Forecasts

Analyze

Description & Overview

Open

Page "Analyze" is designed for building forecast models and in-depth study of forecast influencing factors. The page includes two elements:

Open

• "Parameters" area is designed to select and configure the basic parameters for the forecast calculation;

• "Results" area is designed to show the forecast results, factors that affecting the forecasts, as well as to study their nature.

How we build forecast

MySales has the most technologically and mathematically advanced system core (engine), tested on hundreds of millions different positions and stores, which is responsible for building a stable quality forecast for each position in each store.

The forecast is built at different levels, starting with the most aggregated levels, ending with the most detailed:

• Product group - all stores

• Product group - region

• Product group - store

• SKU - all stores

• SKU - region

• SKU - store

Forecasting is an automatic, multi-stage, iterative process that has a hierarchy and works with a huge data array. When building a forecast, all available history is analyzed at the high levels, up to the last 3-4 years of sales. This is a huge amount of data. Just imagine. If you have, for example 100 stores and 10,000 SKUs, then this is one million combinations multiplied by 3-4 years of sales history. At each recalculation of all forecasts, MySales analyzes gigabytes of information for a small retail chains and terabytes of information for chains with hundreds of stores.

Describing the MySales forecast calculation algorithm, we would like to warn you against trying to implement such an algorithm yourself. Even if you manage to implement such an algorithm in a reasonable amount of time, it will take years to test it on millions of different positions, catching errors, and also spend a lot of effort on optimizing calculation performance to bring it to an acceptable level before you can get economic benefits from using it.

We can distinguish the following main stages of building the MySales forecast, which system performs for each combination at each level:

• Downloading and preparing data from the DBMS, as well as preparing the MySales file storage, which is used to optimize the forecast calculation speed, as well as to reduce the load on the DBMS when processing huge amounts of data. Not only historical sales, prices, discounts, balances, arrivals are loaded, but also the product hierarchy, product directory, geographic hierarchy, store directory and external data (weather, macroeconomics, competitor prices)

• Inclusion of data for analogues by stores or by position. At the same time, the system always sees the latest sales data for a new store or new position and uses analogues data only for those periods where there is no information about the new product

• Formation of data packages for forecast calculation in a multiprocessor environment using multiple (usually from 3 to 9) threads

• Primary cleaning of sales data from key influencing factors to calculate trend and seasonality. This stage is important in order to separate the impact of prices, discounts and promotions on sales and correctly calculate seasonal uplifts. Considering that in retail the amount of historical data for many SKUs is rarely large enough to exclude periods where the influence of discounts or prices took place due to the constant rotation of the assortment. So, MySales, instead of excluding it, cleaning forecast from the influence of these factors in order not to reduce the already limited history sales, excluding only the most extreme periods. Also, at all stages, when analyzing sales, MySales excludes periods with significant sales losses due to the fact that the product was absent or it was not enough on stock to ensure sales. This approach gives the advantage that, in fact, the trend and seasonality are calculated correctly even if the sales history is limited to only one year. And missing periods may be filled from higher forecasting levels

• Seasonality calculation. MySales considers both multiplicative (seasonal coefficient) and additive seasonality. This is necessary choose the most optimal method of seasonality application after analyzing whether the volatility of the seasonal periods increases along with the trend (general growth or decline in sales). Moreover, for the product groups level, seasonality of the average price of the group is also calculated, which is necessary to predict the average price of the group over a long horizon, since seasonal peaks usually have a higher average price in the group.

• Calculation of the trend of overall growth or decline in sales. It is also carried out after cleaning sales from the main influencing factors (price, discount, promotional), as well as after cleaning from seasonality. The system also calculates average sales and median using cleared sales

• Filling in the original matrix of historical values of predictors (influencing factors). A number of predictors are calculated values, for example, the ratio of the price for the current period to the average price for previous periods

• Analysis how sales depends on influencing factors (price, discount, weather, macroeconomic factor, which most often acts as the exchange rate, cannibalization, etc.). When calculating each influencing factor, the system selectively cleans it of other, most significant influencing factors, for example, of promo and seasonality. When analyzing price dependence, the system also analyzes the trend of inflation or deflation in order to clear historical prices from such an impact. A number of factors are analyzed separately for the low, high and medium seasons, so that price elasticity, for example for ice cream, differs for winter and summer

• If it is not possible to determine the dependencies of the influencing factors at detailed levels, then the system takes key ones (for example, the influence of price, seasonality) from higher levels. For example, for the SKU-store level, such dependencies can be taken from the SKU-region or SKU-all stores level, from the group-store, group-region, or group-all stores levels

• Filling the target matrix of future predictor values. Here, a differentiated approach is used, which for some factors can be a simple average or median, for some - predicted values, and for some - information that was entered by the user in the customer’s system and loaded into the MySales data warehouse. It is recommended that you always load into MySales the assortment matrix, future prices as soon as they become known and enter the data about promotional activities

• Calculation of correlation coefficients and formation of an automatic forecasting model based on these coefficients using those factors that affect sales

• Testing automatic, as well as pre-configured forecast models. In this case, the predictive model is understood as a set of influencing factors.

• Choosing the model that gives the best accuracy on past sales. When evaluating each model, periods where the product was not enough to ensure sales, as well as promotional periods that have the greatest impact on sales, are excluded

• After the best model is selected, MySales builds forecast for future periods

• A forecast is also carried out with a number of actions aimed at ensuring its stability and reliability, for example, calculating the minimum sales values, calculating the autocorrelation of the model error, in order to adjust the forecast for the coming weeks and make it more accurate

• The next stage is the calculation of promo uplifts. At this stage, the system applies the promotion coefficients of uplift to the forecast generated by a set of neural networks (Dusya), or data from comparable promos, if such was found. Promo uplifts are adapted to the individual characteristics of each predicted position in each store to take into account the individual characteristics of different combinations and their sensitivity to promotional factors. The minimum and maximum limits of the promotion uplifts are also calculated to ensure a stable result for new positions where the history of the promotion is not enough

• After calculating promo uplifts, the system performs rebalancing of the model taking into account all the influencing factors. This is necessary to balance the influence of the price and the promo effect in the promo forecast, because they often have a high correlation

• At this stage, the forecast is ready, now we calculate the safety stock. SS is calculated as the standard deviation of the forecast from sales in previous periods. SS is also, as in the example above with ice cream, different in summer and winter, so the forecast is divided into 3 ranges: high, low and medium and safety stock is calculated separately for each range

• Further, the forecast is used to calculate price recommendations so that you can determine the most optimal price for sales in value or margin

• The final step is to calculate the possible economic effect in the past, in the form of increased sales, or sales losses for periods in which influencing factors were not known to the system, as well as a stocks reduction

It is also worth noting that the system has a separate algorithm and calculation sequence for new positions that do not have an analogue: for such positions, the system uses the sales of the average position in the product group, adjusting them to the price elasticity of the group using the specific price of the new item, and also applying a number of other restrictions and calculations to make the result more stable and accurate.

There is also a separate forecasting algorithm for expanding distribution. Example: a position was sold in 10 of 30 stores in the region, given the good dynamics and potential, the category manager decided to list it in all 30 stores in the region. In this case, the system uses sales dynamics at the level of SKU-region, group-region and group-store to build forecast for this position in a store where there is no sales history and this position is being listed for the first time.

The set of all factors that the system takes into account is set by the user and can be individually adapted. The default set of factors is described in the "Default Predictors" section.

Daily forecast adjustment

After completing all forecast calculation stages, the system adjusts it for the upcoming weeks (usually two, which is a configurable parameter) based on the most recent days of sales data. To do this, the system loads sales data at the SKU-store-day level for the last 28 days (configurable parameter) and selects the most relevant 7 (or fewer, also configurable) days of sales:

• Separating promotional and non-promotional sales. Past promotional sales adjust only the promotional forecast for the next one to two weeks, while regular sales adjust the regular forecast accordingly.

• Filtering out days with insufficient stock. The stock level must be greater than zero and also exceed 30% of the average daily sales (configurable parameter). In some cases, a minimum absolute stock level can be set as a parameter.

• Handling cases of insufficient stock. If sales occurred despite low stock, the system may still consider them under certain conditions. For example, if a given day’s sales exceeded 75% of the forecast for that day, the system applies an upward adjustment factor. The assumption is that if stock had been sufficient, sales would have been higher:

• By 50%, if the product likely ran out in the second half of the day.

• By 25%, if the product likely ran out at the end of the day.

• Filtering out days with significant price variations. Days where the price deviation exceeded 15% (configurable parameter) are excluded.

Calculating lost sales

For days when an item was part of the assortment matrix in the last 1–2 weeks (configurable parameter), the system calculates lost sales or missed demand for days when there was no stock or an insufficient stock level.

Similar to the Daily Forecast Adjustment calculation, insufficient stock means that either:

• The stock level was zero at the end of the day, or

• The stock was less than 30% (configurable parameter) of the forecasted sales for that day.

When distributing the weekly forecast into daily values, the system also applies day-of-week coefficients and considers price elasticity if the price changes during the week.

If the system finds valid sales data from the last 28 days (configurable parameter) that meet the required criteria (i.e., sufficient stock was available, promotional and regular sales are considered separately, and price fluctuations were within acceptable limits), it calculates the average daily sales. This calculation adjusts the identified 7 or fewer (configurable parameter) sales days using the same factors applied in the daily forecast adjustment:

• Day-of-week coefficients

• Price elasticity and discounts

• Seasonality, weather, and other influencing factors

During the adjustment of average daily sales, the system takes into account the seasonality and weather conditions of the week in which the stock shortage occurred, as well as the day-of-week coefficient, price, and discount on the specific date for which the calculation is performed.

As a result, the system generates an adjusted forecast for the specific date.

Lost sales are calculated using the formula:

Lost Sales = max(Forecast} - Actual Sales, 0)

This applies only if stock was insufficient according to the criteria described above.

Lost sales calculated during the forecast process are stored in the FCST_SKU_LOST table, linked to the forecast ID for the last 2 weeks (configurable parameter). Based on this table, the SALES_SKU_LOST table is updated, maintaining a long-term history of lost sales at the SKU-store-day level. Additionally, data may also be aggregated and stored in the SALES_SKU_LOST_WEEK table, which contains weekly-level lost sales information.

Next, the system adjusts daily sales based on influencing factors, aligning past data with future forecast weeks:

• Day-of-week coefficients

• Price elasticity and discounts

• Seasonality, weather, and other factors

Finally, for each future week—separately for promotional and regular sales—the system calculates adjusted average daily sales. The forecast is then fine-tuned within acceptable limits, which depend on the number of selected days and can be defined via parameters.

Parameters

"Parameters" area is designed to choose and configure the basic parameters of the forecast model. It consists of the following categories:

Open

• Stores

• Groups

• SKU

Data selection happens in a next way:

• button  opens the drop down list for selecting data. It shows previously used data, and has an option to select new data when you click on "select...";

Open

• button  allows you to select all the data for relevant category;

• кнопка  позволяет не строить прогноз для отдельных SKU, а строить только на уровне Группы.

Open

Button "Settings" opens additional parameters for configure the forecast (to hide additional parameters, you need to click this button again):

Open

• parameter "End weeek" – is responsible for choosing the last week for which the system will see historical data, even if there is historical data after chosen week (last week of the training sample). Used to verify the constructed forecast;

• parameter "Profile" – selection the type of forecast:

  • "52-weeks" – 52 weeks forecast calculation;

  • "52-weeks log" – 52 weeks forecast calculation with a detailed report on the process of building a forecast model (the report can be seen in the tab "Models");

  • "26-weeks" – 26 weeks forecast calculation ;

  • "Brain 1000" – forecast calculation using a neural network in 1000 iterations;

  • "Brain 3000" – forecast calculation using a neural network in 3000 iterations;

• parameter "Supplier" – supplier selector. The supplier selection is the same as selection store / group.

When you press "run" the forecast calculation begins. Detailed information about the forecast calculation progress is displayed under the progress bar. At the end of the forecast calculation, audible warning will occur.

Open

Results

"Results" area is designed to display the forecast results and the factors that affects them, as well as for studying their nature.

Open

"Results" area consists of two components:

• analysis area – designed for in-depth study of the forecast model, predictors and their influence on the forecast;

Open

• results display area – designed to display the results of the forecast and the values of the parameters.

Open

Button "More" opens additional displaying parameters of the forecast results (to hide additional parameters, you need to press the button "Less"):

Open

You can setup results displaying in next ways:

• change the displaying of forecast date to weekly/monthly;

Open

• select forecast range to display (from the start date to the end date);

Open

• сhange the display of the forecast sales by sales volume or by sales value.

Open

To apply the changes, click "Show".

Additional parameters tab has the pane that allows you to work with files:

Open

• To load previously calculated model to analyze it you have to select file in field "Select a file…" field, and then press load button  ;

• Для сохранения построенной модель прогноза в формате json (для возможности ее загрузки в будущем) нужно нажать кнопку  ;

• save and download the calculated forecast and the configuration matrix (forecast parameters) in csv format press  .

Analysis area

Analysis area is one of the "Results" area components, it is designed for in-depth study of forecast model, its components and their influence on forecast. Area is used to manually analyze the forecast by SKU, to understand forecast numbers, to analyze the factors that affect it. This is a very important part of the software, since it allows the user to get complete information about the influence of various factors on the forecast, to understand how sales change with price changes, and also to see in numerical terms how different factors will change sales.

Analysis area is represented by header and elements panel.

Header displays:

Open

• Group Name / SKU;

• Stores count / Store name;

• – button for downloading results into csv file.

Elements panel allows you to get detailed information about all positions and consists of next elements:

– drop-down list, which elements allow analyzing sales and forecasting model by SKU. It consists of:

Open

• SKUs chart – visualizes "Components" element in the form of a chart for all SKUs (the user himself selects which component to display on the chart). Details on all components are described in the Forecast analysis components guide;

Open

• SKUs table – visualize "Components' element values as a table for all SKU (the user himself selects which component to display on the chart);

Open

• SKUs list – allow selecting for analysis forecast model for a particular SKU. The forecast model for the selected SKU is displayed as a separate area under the parent area (in list, SKU element disappears);

Open

Stores – drop-down list, which elements allow analyzing sales and forecasting model by Store. It consists of:

Open

• Stores chart – visualizes "Components" element in the form of a chart for all stores (the user himself selects which component to display on the chart). Details on all components are described in the Forecast analysis components guide;

Open

• Stores table – visualize "Components' element values as a table for all Stores (the user himself selects which component to display on the chart);

Open

• Stores list – allows selecting for analysis forecast model for a particular Store. The forecast model for the selected Store is displayed as a separate area under the parent area (in list, Store element disappears);

Open

Components – Allows you to add a new component, parameter, result or characteristic of the calculated forecast model to the results display area. Different components display either their influence on the forecast in sales volume or value, and also display historical values of factors that affect the forecast. The use of components allows a more detailed study of the influence of factors on the forecast, as well as understanding why the forecast has one or another value. Anomaly sales and excluded weeks are also added using components (described in detail in the Anomaly & Excluded section). After being added, the component disappears from the list; The component is returned to the list after it is removed from the display area. For more detailed information about the "Components" elements, use the Forecast analysis components guide; section;

Open

Forecast – designed for visual analysis of the forecast results on the chart. The chart allows you to visually estimate built forecast, as well as using components to understand the forecast behavior (for example, using the stock component, you can see changes in the stocks balance and understand that, for example, sales fell precisely because of shortages);

Open

By default chart displays historical sales, forecast, and historical sales shifted by 52 weeks to the right (for visual forecast estimation) Also chart displays selected components. The user can turn off the display of any element by clicking on its name under the chart.

Open

Predictors – designed for visualization and assessment of the impact of predictors on the predictive model (those predictors that were included in the model are displayed). Allows you to analyze, because of what parameters the forecast has one or another value. For more information on predictors, see Predictors. This element is very important for understanding the forecast itself. It displays the numerical values ​​of the influence of various factors on the forecast and understand on what exactly the sales depend in different periods. User can turn off the display of any element by clicking on its name under the chart.

Open

Price – designed to visualize the chart of price elasticity of demand. This chart allows the user to see how demand changes when the price of a product changes using price elasticity. The system calculates average sales in volume, value and margin relative to different prices. The system also calculates theoretically optimal price values ​​to maximize sales in value and margin. The area around the chart line indicates the possible range of sales for a particular price value. It is built based on the forecast error, it is logical that the larger the error, the larger the area and the greater the range of predicted sales values.

Open

There are 3 interpretations of price elasticity (depending on what it is considered). To select, click on the required field; the current price value is indicated by a dot on the graph):

• Volume – influence on sales volume, purchase price – estimated purchase price;

Open

• Value – influence on sales value, purchase price – estimated purchase price, best sales price – price, that, theoretically gives the highest sales;

Open

• Margin – influence on sales margin, purchase price – estimated purchase price, best sales price – price, that, theoretically gives the highest margin.

Open

Trends – designed to visualize the influence of prices, discounts and weather predictors on sales on the chart with a range of error. It allows the user to see how changes in these factors will change sales.

Open

The necessary parameter is selected from the elements of the "Predictors" drop-down list; if the necessary parameter is not in the list, the influence of this factor is not observed.

Open

There are 2 interpretations of influence (current value is marked with a dot):

• Volume – influence on sales volume;

Open

• Value – influence on sales value.

Open

Models – designed to study and analyze forecast model, to study the influence of various predictors, to analyze reports on model calculation, to select another forecast model in case of disagreement with the model selected earlier.

Open

The element has 3 display variants:

• general – for the aggregated forecast model of stores and SKU, is displayed when the model tab is selected at the group or SKU level until individual stores are selected. Displays models for all selected stores, as well as for regions.

Open

• normal - displayed after selecting a specific store. It can be displayed for all SKUs as well as for selected ones (to select this parameter, you have to choose one particular store), it displays:

  • Forecast estimate - shows values for different forecast estimates;

  • Tested trial models - built models, their assessment, the impact of the predictor options previously specified in the file for each model. The model that the system has selected as the best based on the standard error is highlighted in green. The user can manually change the model by clicking next to the selected model in the "Fix"

  • Correlation Coefficients - coefficients of dependencies of different components on each other and on sales;

  • Trends - formulas for recovering the values of forecast elements;

Open

Open

• detailed – for detailed studying of the forecast calculation process model, it is displayed as a log of calculation process and works only in the "52-weeks log" mode (log automatically appears in Model area)

Open

Results display area

Results display area – is one of the "Results" area components, that is used to display forecast results, historical data values, recovered data, and other resulting components.

Open

By default, the following components are displayed:

• week in ISO format;

• historical sales volumes (or values) for the relevant week;

• sales volume (or values) forecast for the relevant week;

• historical sales volumes (or values), shifted 52 weeks ahead in time, for the relevant week.

Also, it is possible to add other components by using the analysis area component "Components"; for more detailed information about the components, use the "Forecast analysis components guide" section.

Forecast analysis components guide

Components of the forecast analysis (element "Components") are designed for detailed analysis and study of the calculated forecast model.

Components of the forecast analysis are divided into the following categories:

• volume – components that display the results of the forecast in the form of sales volumes;

• value – components that display the results of the forecast in the form of sales values;

• original – components that display historical data and intermediate forecast results (predictors that were used at any of the forecast stages) based on historical data;

• competitors - components that display competitors price for the selected SKU from competitors;

• regressed – сomponents that represents the influence of price factors, weather factors and the width of the assortment of the group;

• economy – components that represents the economic effect when correctly used by MySales;

• models – components that represents forecast when using alternative forecast models (not shown for aggregated models).

Category 'Volume'

Category volume consists of the following components:

• order – represents the sales forecast with safety stock (recommended results for ordering);

• seasonality – represents the influence of the seasonality on sales volume (taking into account the coefficient of influence on the forecast);

• trend – represents the influence of the trend on sales volume (taking into account the coefficient of influence on the forecast);

• region – represents the region sales influence on sales volume (taking into account the coefficient of influence on the forecast);

• group – represents the group sales influence on sales volume (taking into account the coefficient of influence on the forecast);

• auto error – represents the influence of unknown factors on sales volume (taking into account the coefficient of influence on the forecast). It is based on the avg error component, and the duration of the component effect can be 2, 4, or 6 weeks, depending on which duration gives the best result (min error);

• min – represents the influence of the sales conversion on sales volume, in the case of a forecast below the historically limiting volume (taking into account the coefficient of influence on the forecast). The limiting sales volume is the lower quartile of sales by default;

• price % – represents the price changing influence on sales volume (taking into account the coefficient of influence on the forecast);

• discount – represents the discount influence on sales volume (taking into account the coefficient of influence on the forecast);

• discount % – represents the discount (in percent) influence on sales volume (taking into account the coefficient of influence on the forecast);

• rate – represents the dollar rate influence on sales volume (taking into account the coefficient of influence on the forecast);

• a. price – represents the actual price (price with discount) influence on sales volume (taking into account the coefficient of influence on the forecast);

• price – represents the price influence on sales volume (taking into account the coefficient of influence on the forecast);

• item count. – represents the influence of the width of the available assortment (the width of the assortment on the stock) on the sales volumes (taking into account the coefficient of influence on the forecast);

• group disc – represents the influence of the average discount of all SKUs in the product group that the SKU belongs to (taking into account the coefficient of influence on the forecast);

• group price – represents the influence of the average price of all SKUs in the product group that the SKU belongs to (taking into account the coefficient of influence on the forecast);

• base – represents the base sales level (taking into account the coefficient of influence on the forecast);

• temp. – represents the average air temperature during the week influence on sales volume (taking into account the coefficient of influence on the forecast);

• rain – represents the proportion of raining days of the week influence on sales volume (taking into account the coefficient of influence on the forecast);

• snow – represents the proportion of snowing days of the week influence on sales volume (taking into account the coefficient of influence on the forecast);

• anomaly - displays the volume of anomaly sales, and also allows you to enter the value of anomaly sales in the opened field. Anomalies are described in detail in the section 'Anomaly & Excluded';

• исключения - displays excluded weeks, and also allows you to exclude weeks in the field that opens. Excludes are described in detail in the section: 'Anomaly & Excluded'.

If any components from the list are not displayed, this means that they were not included in the predictive model as predictors.

The sign ® or the prefix "reg" before the component means that this component is present in the recovered value (regressors).

Category 'Value'

Category value consists of the following components:

• sales – historical sales value;

• forecast – forecast of sales value;

• last year saels – historical sales value, shifted 52 weeks ahead in time;

• order – represents the sales forecast with safety stock (recommended results for ordering);

• seasonality – represents the influence of the seasonality on sales value (taking into account the coefficient of influence on the forecast);

• trend – represents the influence of the trend on sales value (taking into account the coefficient of influence on the forecast);

• region – represents the region sales influence on sales value (taking into account the coefficient of influence on the forecast);

• group – represents the group sales influence on sales value (taking into account the coefficient of influence on the forecast);

• auto error – represents the influence of unknown factors on sales value (taking into account the coefficient of influence on the forecast). It is based on the avg error component, and the duration of the component effect can be 2, 4, or 6 weeks, depending on which duration gives the best result (min error);

• min – represents the influence of the sales conversion on sales value, in the case of a forecast below the historically limiting volume (taking into account the coefficient of influence on the forecast). The limiting sales volume is the lower quartile of sales by default;

• price % – represents the price changing influence on sales value (taking into account the coefficient of influence on the forecast);

• discount – represents the discount influence on sales value (taking into account the coefficient of influence on the forecast);

• discount % – represents the discount (in percent) influence on sales value (taking into account the coefficient of influence on the forecast);

• rate – represents the dollar rate influence on sales value (taking into account the coefficient of influence on the forecast);

• a. price – represents the actual price (price with discount) influence on sales value (taking into account the coefficient of influence on the forecast);

• price – represents the price influence on sales value (taking into account the coefficient of influence on the forecast);

• item count. – represents the influence of the width of the available assortment (the width of the assortment on the stock) on the sales values (taking into account the coefficient of influence on the forecast);

• group disc. – represents the influence of the average discount of all SKUs in the product group that the SKU belongs to (taking into account the coefficient of influence on the forecast);

• group price – represents the influence of the average price of all SKUs in the product group that the SKU belongs to (taking into account the coefficient of influence on the forecast);

• base – represents the base sales level value (taking into account the coefficient of influence on the forecast);

• temp. – represents the average air temperature during the week influence on sales value (taking into account the coefficient of influence on the forecast);

• rain – represents the proportion of raining days of the week influence on sales value (taking into account the coefficient of influence on the forecast);

• snow – represents the proportion of snowing days of the week influence on sales value (taking into account the coefficient of influence on the forecast);

• anomaly - displays the value of anomaly sales, and also allows you to enter the value of anomaly sales in the opened field. Anomalies are described in detail in the section 'Anomaly & Excluded'.

If any components from the list are not displayed, this means that they were not included in the predictive model as predictors.

The sign ® or the prefix "reg" before the component means that this component is present in the recovered value (regressors).

Category 'Original'

Category original consists of the following components:

• seasonality – represents the seasonality of sales;

• trend – represents the trend influence on sales;

• a. price – represents the actual price (price with discount);

• price – represents the price;

• price % – represents how many times the price has changed;

• discount – represents the discount;

• discount % – represents the discount (in percent);

• stock – represents the goods balance on stock;

• group price – represents the average price of all SKUs in the product group that the SKU belongs to;

• group disc. – represents the average discount of all SKUs in the product group that the SKU belongs to;

• region – represents the region sales redestribution influence on sales;

• group – represents the group sales redestribution influence on sales;

• rate – represents the dollar rate;

• rate % – represents the changing in the dollar rate (how many times has it changed);

• seas. mult – represents the seasonal increase in sales in the form of coefficient (how many times will sales increase);

• avail – represents the availability of goods (enough was the goods in the stock for its maximum sale). In store level displaying a "0" or empty space – the product was unavailable, "1" – the goods was enough. In store aggregated level the component represents the number of stores where the goods were avail;

• temperature – represents the average air temperature during the week;

• temperature, Δ – represents the difference between the average temperature for a particular week and the average temperature for the last 13 week

• rain – represents the proportion of raining days of the week;

• snow – represents the proportion of snowing days of the week;

• seas. type – represents a season type (value of 0 for the normal season, -1 for the low season and 1 for the high);

• promo ratio – represents number of days per week in percentage for which promo was held;

• avg. error – represents the average error of forecast;

• auto error – represents the influence of unknown factors on sales volume. It is based on the avg error component and the duration of the component effect can be 2, 4, or 6 weeks, depending on which duration gives the best result (min error);

• median – represents the median of sales;

• base – represents the base sales level;

• min – represents the influence of the sales conversion on sales volume, in the case of a forecast below the historically limiting volume. The limiting sales volume is the lower quartile of sales by default;

• item count – epresents the width of the available assortment (the width of the assortment on the stock);

• receivings – represents the sum of all goods receiving in stores (from the supplier or from the warehouse), minus the write-offs of shortages;

• # of Stores – represents the count of stores in which group or SKU is represented (available at the region level).

Category 'Regressed'

Category regressed consists of the following components:

• reg. a. price – represents the actual price (price with discount) influence on sales;

• reg. price – represents the price influence on sales;

• reg. price % – represents the price changing influence on sales;

• reg. disc. –represents the discount influence on sales;

• reg. disc. % – represents the discount (in percent) influence on sales;

• reg. rate – represents the dollar rate influence on sales;

• reg. rate % – represents the dollar rate changing influence on sales;

• reg. item count – оrepresents the influence of the width of the available assortment (the width of the assortment on the stock) on the sales;

• reg. temp. – represents the average air temperature during the week influence on sales;

• reg. rain – represents the proportion of raining days of the week influence on sales;

• reg. snow – represents the proportion of snowing days of the week influence on sales.

Category 'Economy'

Category economy consists of the following components:

• stock reduce – represents how much the use of the forecast can reduce the balances in the stock;

• sales lost – represents the loss of sales due to a lower forecast;

• sales increase – represents how much the use of the forecast can increase sales.

Use cases

This form is created for sales and forecasting analysis and has a very wide application. The most successful and largest retailers in the world use the expression "Retail is detail".

The "Analysis" form can be used both for forecasts verefication in the process of setting up and implementing the system, and for analyzing various factors in the process of using the system. It allows user to understand and analyze the factors affecting sales. Using this form will help the user to get answers to a wide range of requests while using the system, including, but not limited to:

• What is the sales forecast for a specific product, product group, store, region or the whole chain in volume, value or margin

• Visual estimation of forecast and sales, comparison with last year's sales

• Estimation of forecast components and factors included in it:

  • Estimating the influence of various factors that affects forecast and sales, including prices, discounts, promotions, weather (temperature, rain, snow), macroeconomic factors (for example, exchange rates), seasonality and trend, cannibalization (mutual influence of goods in the group on sales of each friend) and even prices and promotions from competitors!

  • Analyzing the impact of the factors mentioned above on the sales, at the level of the all stores, regions and specific stores

  • Modeling the impact of influencing factors on the future forecast. For example, how sales will change if you lower the price by 10% or increase the discount by 10%

• View sales correlation coefficients and factors that influence the forecast

• View all models tested by the forecasting system and their accuracy, estimated by the coefficient of variation (standard deviation divided by average sales) and absolute error

• View forecast errors on weekly or 4-week ranges, estimated as an absolute error in percent (MAPE), an absolute error in units (MAD), standard deviation in units (RMSE) and standard deviation in percents (RMSPE)

• View mathematical formulas of dependencies between sales and influencing factors, which was determined using automatic regression analysis

• Analysis of products stocks, trx, presentation and safety stocks

• View a detailed forecast calculation log (forecast log in the system)

If you find that for a certain position there are any problems with stock balance, for example, there is a out of stocks, or an overestimated stocks, it is recommended to look in this form to analyze the reasons.

The specific cases that apear while users are working with the system and for which the "Analysis" form provides an answer can be found in Questions / Answers.

View

Overview & Use

Open

Page "View" is designed to display in a convenient format forecast data. The user can choose which data for which items he wants to see.

The list of records is displayed in the form of a table that has the following fields:

Open

• Store - store number;

• Group id – Group ID;

• Name – Group name;

• Week number – data for each week.

Operation manual

Template creation

To create template you have to select "Create New Template".

Open

And after press the button "Create Template".

Open

After clicking the button, a modal window for template creating opens. The user chooses which for which group, store, positions the data will be displayed, as well as display period, margins and accuracy. It consists of the following elements:

Open

• Name - the name of the template;

• Level - the level at which data will be displayed (depending on the choice the appearance of different fields for filling is possible);

• Groups - group numbers;

• Stores - store numbers;

• SKUs – SKU numbers;

• Regions - regions numbers;

• Filter by name - filter positions by name;

• Week from - the week number from which the data displaying will starts;

• Week to - the week number to which the result will be displayed;

• Fcst value – display the forecast in value;

• Sales volume – display the sales in volume;

• Sales price – display the sales price;

• Fcst purch. value – display the forecast in value at the purchase price;

• Sales value – display sales in value;

• Purchase price – display purchase price;

• Fcst master – display master forecast;

• Sales purch. value – display sales in value at a purchase price;

• Safety stock – display safety stock;

• Assort stores -

• Current stock -

• Avg Safety Stock -

• Precision – a number of symbols after the comma.

Template selection

To select an already created template, select the desired template from the drop-down list by clicking on the following field:

Open

To open a template, click "Run". A table with names and data on previously specified positions will open.

Open

Editing and deleting

To edit a template, you have to select the desired template from the drop-down list, and then click "Edit" button:

Open

After clicking the button, a modal window for editing the template opens. Using it, the user can change the same fields that were available when creating, save changes by clicking the button "Save", or delete the template by clicking the button "Delete".

Open

Filter

For a more handy items searching and displaying there is a search string. The search is possible for the following fields:

Open

• SKU id;

• Name;

• Store.

Use cases

This functionality is recommended to be used if it is necessary to upload the forecast and other data (for example, safety stock) for one or several SKUs, several stores, or for groups, with the forecast weeks to be deployed horizontally. If a horizontal spread of weeks is not needed, you can also use the "Reports" functionality.

Examples of situations in which you can use forecast upload:

• Given that the supplier’s production and supply planning cycle is much longer than the retailer’s supply cycle, this functionality will be useful to share SKU sales forecasts with the supplier or distributor, which will allow the supplier to improve the level of service due to long-term planning production, as well as reservation of a certain volume of goods

• Uploading a forecast for product groups will be useful in order to improve the strategic planning process at the beginning of the year/quarter by comparing the sales plan for the top-level categories and the sales forecast for the lower product groups. The difference in the forecast between these levels, when the plan for categories is higher than the total forecast for product groups, as a rule, can be covered by a promotion, listing of additional regular or promotional assortment, opening of new stores.

• Analysis of expanding distribution sales potential by comparing forecasts at different levels. For example, comparing the forecast at the regional level 0 (the whole chain) with the total forecast at the store level often shows the difference in the future (when the forecast at the regional level 0 in the future is greater than the total for stores), which can be covered by expanding the chain and opening new stores

• Analysis of the potential of product groups to expand the assortment. For example, the difference between the forecast at the product group level and the forecast at the SKU level often shows the difference (when in the future the forecast at the product group level is larger than the forecast at the SKU level), which can be covered by rotation/expansion of the assortment in this product group.

Master

Overview & Use

Open

Page "Master" designed to manually set the forecast of a specific SKU for a specific week for all stores. The established forecast is distributed proportionally to all stores during the work of MySales.

Operating manual

Working with Master

Page "Master" has a wide functionality that allows to:

• display a list of forecasts;

• add forecast;

• edit forecast;

• delete forecast;

• apply filters to display forecasts;

• load forecasts from a file;

• download forecast.

The list of forecasts is displayed in the form of a table, which displays the latest version of the forecast and has the following fields:

Open

• Sku id – SKU ID number;

• Sku Name – the name of Sku;

• Week – week on which the forecast was added;

• Type - the type of SKU;

• Stores - stores selection for which the master forecast is distributed;

• All - indicator of the selection of all stores;

• Forecast – manual forecast;

• FIX - indicates whether to fix the specified master forecast if the daily correction is triggered. For example, if the master is not fixed and the system sees that the sale is less than specified by the master, it will automatically lower the master forecast. And if the master is fixed, then the system will leave the master forecast unchanged (values 1 - fix, 0 - do not fix);

• Date from - a field that indicates the start date of the promo (active only for Promo type items);

• Date to - a field that indicates the end date of the promo (active only for Promo type items);

• Updated by – user who last made the changes;

• Updated – date of last change;

• Notes – short remarks.

Filters

For more handy forecasts displaying and searching page "Master" has filters:

Open

• Search line. Search is done by fields:

  • SKU id;

  • Name;

  • Forecast;

  • Updated by.

• Filter by week. Displayed all forecasts whose week is equal to the selected. The current week is selected by default. If the search string is not empty, then becomes possible to select all weeks to display forecasts for all weeks.

• Filter by revisions. Allows you to display all revisions of forecasts (more details about the revisions in the "About revisions"). By default, the filter is off and unavailable. The filter becomes available if the search string is not empty. If using a filter, the table displays the forecast revisions (only the current one can be edited) and the forecasts can be deleted.

Adding forecast

To add a new manual forecast, click the add forecast button.

Open

After clicking the button, opens a modal window for adding a forecast, which consists of the following fields:

Open

• Group – field for selecting the product group. If the user wants to skip the selection of the group and be able to choose from all SKUs in the system, not limited by the group, check the box next to "Not limited by group" (in this case the SKU list will be loaded longer than usual);

• SKU – field for selecting Sku from the selected product group;

• Type - selecting SKU type for which the master forecast is set. There are three types of SKU in the system:

Open

• Other - default type - suitable for all SKUs;

• New item - type for new positions;

• Promo - type for specifying a manual forecast for the position in the promo. When this type is selected, two new fields appear in the form of adding the forecast master:

Open

• These fields are intended for selecting the start and end dates of the promotion. The date must be entered in the format YYYY-MM-DD;

• Week – field for selecting the week for which the forecast is set;

• Forecast – field for setting the forecast of sales volume;

• Notes – field for recording notes for a new forecast.

After filling the fields, click the button "Add". If decision off adding a new forecast is canceled, click the button "Back".

If there is an error when adding a forecast, a modal window appears with an error message.

Open

Editing forecast

The forecast is edited in the table. The "Forecast", "Notes", "Date from", "Date to" fields are editable (date fields are editable only for fields with "Promo" type).

Open

When the "Forecast" field is changed, a new revision of the forecast is created and the "Updated by" and "Updated" fields are updated.

When the "Notes" field is changed, the latest revision changes without creating a new revision. The "Updated by" and "Updated" fields are not updated in this case.

When the "Date from" or "Date by" fields are changed, a new version of the forecast is created and the "Updated by" and "Updated" fields are updated.

Deleting forecast

To delete the forecast click the button .

A window with the forecast data and the possibility to delete it opens.

Open

While using the filter by version, the forecast deleting is not available.

If you delete a forecast, all versions will be deleted. The data in the table is updated when the forecast is deleted.

Master forecast import/ex[ort from files

The user has the ability to upload master forecast from a csv file. There are two types of files:

• File with master forecast for a specific week;

• File with master forecast for a for the period between specific dates;

To upload a forecast from a file, select the file by pressing the button "Select file". After selecting a file, press the button .

Descriptions of the fields of file with master forecast for a specific week:

• SKU_ID - SKU code from MySales;

• WEEK - the week for which the master forecast is added;

• TYPE - master forecast type (1 - Promo, 2 - New item, 3 - Other);

• FIX - indicates whether to fix the specified master forecast if the daily correction is triggered. For example, if FIX = 0 and the system sees that the sale is less than specified by the master, it will automatically lower the master forecast. And if FIX = 1, then the system will leave the master forecast unchanged (takes values 1 - fix, 0 - do not fix);

• FCST - master forecast volume;

• NOTES - additional notes (optional field);

• STORES - stores for which the master forecast is added (if master is added for all stores - leave this field empty).

Example of file with master forecast for a specific week File example.

Descriptions of the fields of file with master forecast for the period:

• SKU_ID - SKU code from MySales;

• START_WEEK - start of the period for which master is added;

• END_WEEK - end week of the period for which master is added;

• TYPE - master forecast type (1 - Promo, 2 - New item, 3 - Other);

• FIX - indicates whether to fix the specified master forecast if the daily correction is triggered. For example, if FIX = 0 and the system sees that the sale is less than specified by the master, it will automatically lower the master forecast. And if FIX = 1, then the system will leave the master forecast unchanged (takes values 1 - fix, 0 - do not fix);

• FCST - master forecast volume;

• NOTES - additional notes (optional field);

• DATE_FROM - start date of the period for which master is added;

• DATE_TO - end date of the period for which master is added;

• STORES - stores for which the master forecast is added (if master is added for all stores - leave this field empty).

Example of file with master forecast for the period File example.

To upload master forecast to a file, press the button .

Open

About revisions

To track changes and save history "Master" does not overwrite the forecast (when updating or downloading from the file), but creates a new revision of the forecast. The revisions of the forecast are displayed when the filter by revisions is applied. When applying the filter, a new field "Revision" is added to the forecasts table. The current version has a value of 0, the relevance of the others is ranked by the increase (the smaller the number the more relevant).

While displaying the forecast revisions, the deleting is not available. Allowed to edit only the current version (whose revision number is 0).

Open

Use cases

The master forecast is used to adjust the forecast taking into account factors that the forecast cannot take into account. This is usually promotional sales (if a promotional module is not used, promotional sales are described in more detail below), new positions for which there is no history , or other non-standard events. In these cases master forecast is set based on an expert estimations.

It is always recommended to verify the promotional forecast for top positions as well as for new products where there is not enough history of the promotions using master forecast adjustments. This is relevant, since there are a number of factors that the system cannot take into account in the forecast, for example:

• Changing market conditions for top positions, such as a significant change in market prices, or the emergence of competing positions.

• Competitors activities that appear systematically with the same geography of coverage, such as expanding or narrowing the assortment, counter promotions, etc.

• Events of a national scale, such as football championships, or other sporting events.

• New ways of communication with the consumer to inform about promotional activities that have not been used before. For example, TV advertising for promos has not been carried out before, but this communication channel will be used in the planned promos. Or, SMS / Viber mailing was not previously conducted, but it is planned to use this channel.

For the cases mentioned above, it is recommended to revise the system forecast at the SKU-entire chain level and set a master forecast with the “Promo” type.

Also, it is possible to use a master forecast in a number of other cases, for example:

• Revision of the forecast for new positions based on information received from the supplier when it is not possible to select an analogue

• Planned narrowing or expansion of the assortment, which can significantly affect the demand for top positions

• Reformatting the store, changing the layout and other factors invisible to the system, which can significantly affect the demand for top positions.

New

Overview & Use

Open

Page "New" allows you to add new SKU positions and calculate the forecast of their sales based on the sales data from similar products. When constructing the forecast, the system takes into account the coefficient of influence of each of the analogs, which is specified when adding a new position.

The list of records is displayed in the form of a table that has the following fields:

Open

• SKU – SKU name;

• Group – group name;

• Analogs – names of similar products;

• Ratio – coefficient of influence for each similar product;

• Week – cutover week;

• Updated – last update date.

Operation manual

Adding new position

To add a new position, click the add new item button (before adding the position, you must add it to the SKU database)

Open

After clicking the button, a modal window for adding a forecast opens, which consists of the following fields:

Open

• Group - group name. If the user wants to skip the selection of the group and be able to choose from all SKUs in the system, not limited by the group, check the box next to "Not limited by group" (in this case the SKU list will be loaded longer than usual);

• New item - new position name;

• Analogs - names of similar products of a new position.

After clicking "Continue" button, the second window opens, in which the coefficients of the influence of analogues are set, as well as the cutover week:

Open

Editing and deleting

To delete new position click button .

After clicking, a modal window opens with the name of the item and a request to confirm the deletion.

Open

To edit new position click button .

After clicking a window with the possibility to change the coefficients of the influence of analogues, as well as the week of clipping opens.

Open

Filter

For more handy displaying and searching the page has SKU filter.

Open

Load data from file

The user has the ability to download data about new positions from the file. To do this, prepare a file in excel-format with the following fields:

• GROUP_ID - group number;

• SKU_ID - new SKU number;

• ANALOGS - a list of analog SKU numbers separated by commas (it is important that analogs should be in the same group with a new position);

• RATIO - the coefficients of influence of each analogue, separated by commas (in total, they should give 1);

• WEEK - week of the start of sales of a new product;

An example of csv file can be found at link: "New items load file example".

Use cases

Section is under development.

Additional load

Overview

Open

Page "Additional load" is designed to set the calculation period for the additional forecast at SKU level - the entire network. This forecast is calculated for the specified period of time for the premature order of goods for this period.

Operating manual

Working with page

Page "Additional load" has a functional thatallows:

• display the SKU list;

• add records about the calculation of the additional forecast;

• delete records about the calculation of the additional forecast;

• edit records on the calculation of the additional forecast;

• Apply filters to display records about calculating an additional forecast;

• download and upload records about the calculation of the additional forecast.

The list of records is displayed in the form of a table that has the following fields:

Open

• Sku id – SKU ID number;

• Name – SKU name;

• Week from – the first week of the period;

• Week to - the last week of the period;

• Updated by - the user who last made changes;

• Updated – last update date.

To add a new record click “Add new record”

Open

After clicking the button, a modal window for adding a new entry appears. When adding a new entry, you must enter the following parameters:

Open

• Group – group to which the desired Sku belongs. If a user wants to skip the selection of the group and be able to choose from all SKUs in the system, not limited by group, check the box next to "Not limited by group" (in this case the SKU list will be loaded longer than usually);

• Sku – SKU for which the record is added;

• Week from – the first week of the period;

• Week to – the last week of the period.

To confirm the addition of a new record, press the button "Add". To return back – "Back".

To edit the record, press the button  in the record line. After pressing the button, a modal window for editing the record appears. It is possible to edit the following parameters:

Open

• Week from – the first week of the period;

• Week to – the last week of the period.

To confirm the editing of the record, press the button "Edit". To return back – "Back".

To delete the record, press button  in the record line.

Filters

For more handy records displaying and searching, the page "Additional Load" contains the following filters (Fig. 47):

Open

• Search line. Search is done by fields:

  • SKU ID;

  • Name;

  • Updated by.

• Filter by period.

Working with files

Page "Additional Load" has the possibility of uploading records from a file and downloading forecasts to a file.

Open

To load forecasts from a file click button "Select file". After selecting a file, click on the button .

"Additional Load" supports loading of 3 extensions of files:

• tsv with separator Tab;

• txt with separator Tab;

• csv with separator ";".

The upload file must have the following fields:

Open

• "SKU" – Sku id for which the record is created;

• "WEEK" – the first week of the period;

• "WEEK TO" – the last week of the period.

To download records in file press . All the records that are displayed in the table are downloaded in file with the following fields: "SKU", "WEEK", "WEEK TO".

Use cases

This functionality is used to provide the possibility of additional loading of stores with goods before special events or a high sales season, in the presence of various logistic restrictions in the operation of the distribution center or suppliers.

The “Additional load” functionality can also be used to load stores with goods at the beginning of the promo campaign for the entire period of the campaign, if such goods have the effect of increased demand in the first days of the campaign and the saturation of demand, which is accompanied by a drop in sales in the following days of the campaign.

It is also possible to use this functionality for additional loading of new stores with goods, in order to ensure peak sales in the early days, when a campaign of active promotion of a new store takes place.

It is recommended to use additional loading only for goods with a long shelf life, which, at the same time, are in the top of sales by volume, since for such items the risk of creating illiquid stocks is the least. It is not recommended to use this functionality for slowly selling positions, since for them there is a high risk of creating an illiquid stock. It is also not recommended for items with a short shelf life in order to avoid damage to the product and, as a result, write-offs or returns.

Enabled items

Overview & Use

Open

Operating manual

Working with page

Page "Enabled Items" has a functional that allows:

• display the list of SKU;

• add SKU to the list of auto-order items;

• exclude SKU from the list of auto-order items;

• apply filters to display SKU;

• download SKU lists.

The Sku list is displayed as a table, which has the following fields:

Open

• Group id – group number to which Sku belongs;

• Sku id – SKU ID number;

• Name – the name of SKU;

• Updated by – the user who last made the changes;

• Updated – date of last change.

To add Sku to the list of auto-order items, tick the last column of the table. To exclude Sku, you need to remove the checkmark. Sku is not added to the list of auto-order items by default.

The additional functionality menu (Fig. 41) appears on click the button

Open

• Select all – allows you to add all Sku (with applied filters) to the list of auto-order items;

• Delete All – allows you to exclude all Sku (with filters applied) from the list of auto-order items;

• Export in tsv – allows you to download all Sku (with applied filters).

Filters

For more handy SKU displaying and searching the page "Enabled Items" contains the following filters:

Open

• Search line. Search is done by fields:

  • Group id;

  • Sku id;

  • Name;

  • Updated by.

• SKU display filter. Displays:

  • All – list of all SKU;

  • Selected – list of all SKU added to the list of auto-order items;

  • Deleted – list of all SKUs not added or excluded from the list of auto-order items.

Use cases

This functionality usually is used if the auto-ordering functionality is not implemented by the MySales, but by the existing customer auto-order system which uses the forecasts and the safety stock from MySales in the auto-order calculation formulae.

The “Enabled items” functionality does not affect the calculation of the forecast or order in MySales. However, if necessary, it can also be used in MySales for setting various kinds of restrictions for SKU lists.

When integrating forecasts and the MySales safety stocks into the auto-order formula of the customer’s system, it is recommended to use this functionality in order to gradually switch positions from the existing order calculation formula to a new one based on the MySales forecast and safety stock.

So when you start working with MySales, the user has the possibility to choose the positions for which MySales will calculate the forecast and safety stock for auto-order. For positions that are not selected in this form, the order will be calculated according to the old scheme - using forecast and safety stock calculated by customers auto-order system. And only for the selected positions, the auto-order system will take the forecast and safety stock, which is calculated by MySales.

This form allows customer to make a soft transition from forecasts that were calculated in existing auto-order system to MySales forecasts.

Safety stock adjustments

Overview & Use

Open

Page "Safety Stock Adjustments" is designed to set the safety stock coefficient for auto-order.

Safety stock coefficient can be set for the next levels:

• SKU-All stores - the set coefficient applies to all stores;

• Store - coefficient applies to all SKUs in the selected store;

• SKU-Store - the coefficient is applied for a specific pair of sku-store.

The calculation of the safety stock is automatic, you can adjust it using the safety stock coefficients on the page.

Safety stock for each position is calculated on a weekly basis and is equal to the value of RMSE (root mean square error) for the forecast for the last 52 weeks. For example, if the RMSE at week 46 was 35, then the automatic safety stock for the position would be 35. The system automatically divides the forecast into 3 ranges: high, medium and low. The high range includes high sales season and promotional periods, the low range includes periods of seasonal decline in sales, and the middle range includes everything in between. For each range, safety stock is calculated separately (taking into account sales of only the corresponding range).

How we apply SS Adjustments

A change in safety stock coefficients without understanding how this affects orders volume and this can lead to a large over-order or under-order, which leads either to overstock or lost sales due to out of stock.

The safety stock coefficient can be raised only after all round estimation of the adequacy of the forecast and the safety stock values. The coefficient can never be raised for individual drops to out of stock. We recommend raising safety stock only for top positions.

To make a decision to increase the safety stock, you should be guided by the following criteria:

• Shelf life - for the fresh products it is necessary to estimate whether there will be an over stock, which will lead to write-offs. For these products, it is necessary to find a balance between lost sales and write-offs;

• Delivery frequency - worth considering that the SS coefficient is applied with the square root function. Thus, with daily delivery it will be counted in the order as ROOT SQUARE (1/7), with weekly delivery - as a unit from the level that you see in MySales;

• Value of product for the company (margin) - for top positions, we recommend, if necessary, to raise SS (usually, valuable positions are those with a high sales rate);

• Sales speed (the higher sales speed, the greater chance that an safety stock will be eaten) - for positions with a high sales rate, usually these are top positions that carry great value for company, it makes sense to increase the value of SS to increase availability;

• Sales volatility (unpredictable positions that do not have patterns of sales fluctuations) - if the sales are very different from week to week and any patterns are not visible in these differences (the influence of price, seasonality, weather, the trend - all can be checked in the MySales interface), and at the same time, this position sells well, or brings good margin to the company, it makes sense to increase the SS coefficient so as not to miss the unpredictable jumps in sales. At the same time, it is important not to forget to evaluate the shelf life, if it is a fresh.

In general, you should use system approach for working with SZ, analyzing the history of sales, forecast and safety stock in the MySales interface. To do this, you need to add the Order component (which represents the forecast + weekly SS) and estimate the forecast quality and the adequacy of the safety stock on the chart, visually. It is necessary to estimate not only the current week, but also history.

Also, you do not need to immediately raise the SS coefficient when an out of stock occurs. It is necessary first to check the nature of the problem, since raising SS after a single loss leads to a over order.

Operating manual

The coefficient is intended for manual adjustment of the safety stock. With it, the user can manually change the safety stock value for the position. The user can both increase and decrease the safety stock. The system multiplies automatically calculated safety stock with coefficient value.

To increase the safety stock, the user have to set a coefficient greater than one. For example, if the system automatically calculated the safety stock is 35, when setting the coefficient 2, the safety stock will be equal to 70, similarly if you set 3, the stock will be 105. You can also set fractional coefficients, with a coefficient of 1.6 the safety stock will be 56 (since 35 * 1.6 = 56).

To reduce the safety stock, the user have to set a coefficient less than one. For example, if the system automatically calculated the safety is 35, when setting the coefficient 0.6, the safety stock will be equal to 21, similarly if you set 0.4, then the safety stock will be 14.

The changed value of the safety stock coefficient will remain in effect until the user change changed. The coefficient will change automatically every week. For example, if the ratio is set to 2, then next week the automatically calculated value of the safety stock will also be multiplied by 2.

To return safety stock to the default value, you need to remove the value from the coefficient field. You can also do this by setting the coefficient value to 0 or 1 (when setting the value to 0, the coefficient field will be automatically cleared).

To upload safety stock coefficients to a file, click the button. :. Data will be written to an Excel file.

Setting coefficients at the SKU-All stores level

To set the safety stock coefficient at the SKU-All stores level, select "SKUs" in the level selection line:

Open

After selection, a window opens with a table with all SKUs in the system:

Open

The table has the following fields:

• Group id – group number to which Sku belongs;

• Sku id – SKU id from MySales;

• Name – the name of Sku;

• Updated by – the user who last made the changes;

• Updated – date of last change;

• Coefficient – safety stock coefficient of Sku.

The coefficient is edited in the table. The "Coefficient" field is editable.

Open

When the "Coefficient" field is changed the new safety stock coefficient is saved and the fields "Updated" and "Updated by" are updated.

For more handy SKU searching and displaying the page contains the search line. The search takes place by fields:

• Group id;

• Sku id;

• Name;

• Updated by.

Open

Setting coefficients at the Store level

To set the safety stock coefficient at the Store level, select "Stores" in the level selection line:

Open

After selection, a window opens with a table with all Stores in the system:

Open

The table has the following fields:

• Store id – Store id from MySales;

• Name – the name of Store;

• Updated by – the user who last made the changes;

• Updated – date of last change;

• Coefficient – safety stock coefficient of Sku.

The coefficient is edited in the table. The "Coefficient" field is editable.

Open

When the "Coefficient" field is changed the new safety stock coefficient is saved and the fields "Updated" and "Updated by" are updated.

Setting coefficients at the SKU-Store level

To set the safety stock coefficient at the Store level, select "SKUs/Stores" in the level selection line:

Open

After selection, a window with a table will open, in which records of SKU-Store pairs for which the safety stock coefficient is set will be displayed (if there are no such pairs, the table will be empty):

Open

To add a coefficient at the SKU-Store level, you must first add the SKU-Store pair. To do this, select the desired SKU in the "Select SKU" field, select the desired store in the "Select store" field and click the "Add" button:

Open

After clicking "Add" a pair of SKU-Shop will be added to the table. The following fields are displayed in the table:

• Sku id – SKU id from MySales;

• Name – the name of Sku;

• Store id – Store id from MySales;

• Name – the name of Store;

• Updated by – the user who last made the changes;

• Updated – date of last change;

• Coefficient – safety stock coefficient of Sku.

The coefficient is edited in the table. The "Coefficient" field is editable.

Open

When the "Coefficient" field is changed the new safety stock coefficient is saved and the fields "Updated" and "Updated by" are updated.

Import coefficients from a file

On the safety stock adjustment page, to simplify the process of adding new coefficients, it is possible to immediately upload a large number of coefficients from files with next extensions: csv (with delimiter ;) and txt (with delimiter ;).

To load safety stock coefficients from a file, click on the button :

Import coefficients at SKU-All stores level

For the correct import, the file must have the following fields:

• SKU_ID - column with SKU id from MySales;

• SS - column with safety stock coefficient.

Import coefficients at Store level

For the correct import, the file must have the following fields:

• STORE_ID - column with Store id from MySales;

• SS - column with safety stock coefficient.

Import coefficients at SKU-Store level

For the correct import, the file must have the following fields:

• SKU_ID - column with SKU id from MySales;

• STORE_ID - column with Store id from MySales;

• SS - column with safety stock coefficient.

Use cases

It is recommended to increase the safety stock coefficient when switching to an order based on the forecast for the following positions:

• TOP 100/500/1000 sales volume postions for which shelf life allows you to keep an increased stock in order to increase availability. At the same time, for TOP 100 it is possible to consider raising the safety margin to 3, for TOP 500 it is recommended to use coefficient 2, while for TOP 1000 it is possible to consider the use of coefficient 1.5. The general rule of statistics says that the higher the sales rate of a position, the more accurate the forecast, respectively, the lower the safety stock. However, unpredictable sales surges still happen, therefore, an increase in the SS coefficient for such positions is justified.

• Positions, which are margin generators and are valuable to the company. Such items, for example, may include company own brands products with a long shelf life, which allows to increase the safety stock in order to increase availability. If this position is not in the TOP, as a rule, the SS 2 coefficient is quite enough. It is also possible to consider coefficient 1.5

• Fresh products with a limited shelf life, including vegetables and fruits, dairy products, bread, and other products with a shelf life of slightly more than the delivery cycle. For such goods, it is not recommended to use the SS coefficient above 1, and in some cases it may be advisable to reduce it to 0.5 or even to 0 if there is a goal to have a zero stock on them for the next morning.

Forecast Adjustment

Description

Page "Forecast Adjustment" is intended for manual adjustment of the forecast for the selected week for SKU-Store combinations.

Manual adjustment can be set as a fixed forecast value, or as a coefficient by which the forecast calculated by the system will be multiplied.

Manual forecast is always a priority, and the forecast will always be equal to the value that is set on this page.

It is also important to understand that if the user has set a master forecast and made an adjustment based on the coefficient, then the coefficient will not be multiplied by the initial forecast of the system, but by the already distributed master forecast. But if the correction is set based on a fixed forecast value, then the distributed master forecast will be overwritten by the value from the "Forecast adjustment" form.

Adding forecast adjustment

The user can add the adjustment in three ways:

• For one SKU-Store

• For several stores

• From file

To add one combination, select SKU and Store from the corresponding fields and click the "Add" button.

Open

After pressing the button, the selected combination will appear in the list where the user sets either a coefficient or a fixed forecast value. It is important to remember that you can set only one of two values - either a coefficient or a forecast.

To add a combination of SKU and several stores at once, you need to click the "Create" button, after clicking, the window for adding corrections will open:

Open

With this method of adding, the user sets the forecast value for all selected stores, and then the system itself distributes the set value between the stores, based on sales interval specified in this window.

Import from file

To simplify adding adjustments, it is possible to load data from a file.

To import adjustments from a file, click on the  button:

For correct import, the file must be in csv or txt format with a semicolon delimiter (;). The file must contain the following fields:

• WEEK - week for adjustment;

• SKU_ID - column with SKU number MySales;

• STORE_ID - column with Store number MySales;

• COEF - the coefficient by which the forecast should be multiplied;

• FCST - fixed forecast value;

All columns should be present in the file, but for one SKU-Store combination it is permissible to fill in only one value - either COEF or FCST.

Fractional values in the fields COEF and FCST must be entered through a point (for example 1.4).

Sample import file available at link.

Anomaly & Excluded

Overview & Use

Open

Page "Anomaly" designed to output the number of anomaly sales in stores (if the user previously on the page "Analyze" indicated anomaly sales), as well as to output excluded weeks from the forecast at different levels by the user (if the user previously indicated excluded weeks on the "Analysis" page).

Anomaly sales are sales that are non-standard. Typically, with such sales, the system either overestimates or underestimates the forecast, because it does not understand the nature of such sales. It can be wholesale sales or just a large volume of sales of ordinary products without any reason.

Such sales must be excluded from the forecast. There are two options for how to do this:

• If the user understands the amount of such sales - he should enter a specific (or as close as possible) number of anomaly sales into the system, then the system will see the sales as actual minus the specified anomaly ones;

• If the user does not understand the amount of such sales, it makes sense to completely exclude the week from the forecast (how to do this is described in the section Working with excluded tab).

Accounting for anomaly sales is very important for the correct operation of the system. Since unjustified jumps in sales can cause incorrect dependencies in the system and in the future affect the accuracy of the forecast and order.

Operating manual

Working with anomalies tab

In order to see the data in "Anomalies" tab, user must indicate the presence of anomaly sales on "Analyze" page.

To do this, you first need to open a forecast at the level of one SKU.

Open

Then open "Components" tab , select "Volume" and press "Anomaly".

Open

After clicking on "Anomaly" a line appears in the window, in which you can enter the number of anomaly sales for each week. To close a line press button - .

Open

The list of anomalies is displayed in the form of a table that has the following fields:

Open

• Group - the name of the group to which SKU belongs;

• SKU - SKU name;

• Store - the name of the store;

• Anomalies - the number of anomaly sales and a week.

Anomalies tab filters

For more handy data displaying, "Anomalies" tab has following filters:

• By level - to display data in a section of SKU or a group (to change the level, click on the desired field);

Open

• Consolidation by positions:

Open

• Detailed display of all table positions;

• By SKU - display of positions without shops;

• By Groups - mapping only groups and anomalies;

• By Stores - display only stores and anomalies.

• By period - the choice for which period to display the data (to confirm the change of the period, you need to press "Apply" .

Open

Working with excluded tab

To open the Exceptions tab click the following button:

Open

In order to see the data in "Excluded" tab, user must set excluded sales on "Analyze" page. To do this, open the tab "Components", select "Volume", and then, press "Excluded" at any forecast level.

After clicking on "Excluded", a line appears in the window, in which you put a tick under the week, which should be excluded from the forecast. To close a line press button - .

Open

The exception list is displayed as a table that has the following fields:

Open

• Group - the name of the group to which SKU belongs;

• SKU - SKU name;

• Store - the name of the store;

• Excluded - the number of exclusions and a week.

Excluded tab filters

For more handy data displaying, "Excluded" tab has following filters:

• By level (to change the level, press to select the desired field);

Open

• In the SKU cut (by default);

• In the Group cut:

Open

• Consolidation by positions:

Open

• Detailed display of all table positions;

• By SKU - display of positions without shops;

• By Groups - mapping only groups and excluded;

• By Stores - display only stores and excluded.

• By period - select for which period display the data (to confirm the change of the period, you need to press "Apply" .

Open

Use cases

The use of anomalies and exclusions is useful for finer tuning of the sales history, in order to improve the quality of the forecast. Using this functionality, the system will better understand non-standard deviations in the sales history.

Anomalies should be used in the following cases:

• Designation for the system of lost sales for those periods where it is difficult to distinguish them. For example, the products were listed on the stock, but was actually not available for sale for a certain time (for example, half a day for 2-3 days a week)

• Designation for the system of lost sales for periods, which exclusion from the analysis will not improve the quality of the forecast, since these weeks are limited by periods and help the system to determine the dependencies valuable for forecasting. For example, promotional periods

• The allocation of sales on pre-order, wholesales, or other pre-planned sales, which are one-time and are not repeated and massive. However, anomalies use in such a situation can only be justified with a limited sales history. If there is enough history, the use of exclusions will be better.

Exclusions should be used in the following cases:

• To exclude periods with significant lost sales for those positions where there is enough history and an insignificant decrease in the number of periods for analysis will not lead to a decrease in the forecast quality

• To exclude periods with significant pre-order or wholesale sales for positions where a regular sales history is sufficient for analysis

• To exclude promotional periods from the analysis if the PROMO module is not used and MySales forecast is built for regular and seasonal sales, excluding promotional growth

Bad positions

Overview & Use

Open

Page "Bad items" allows the user to see on which positions a bad forecast is calculated. After each forecast build on the page "Analyze", the system automatically adds positions with the biggest error on page "Bad items".

Список плохих позиций отображается в виде таблицы, которая имеет следующие поля:

Open

• Group - Group name;

• SKU – SKU name;

• Store – Store name;

• MAPE – mean absolute percent error;

• First Date - the date of the first forecast, in which a bad position appeared;

• Last Date - the date of the last forecast, in which a bad position appeared.

Filters

For more handy displaying the page has following filters:

Open

• SKU/Group – a selection of mapping in the SKU/Group view;

• By MAPE – the table is sorted by the highest MAPE value;

• By First Date – the table is sorted by the first date;

• By Last Date – the table is sorted by the last date.

To clear data about bad positions, you have to press the button "Clear".

Open

Statistics

Open

Page "Statistics" displays detailed statistics of each calculated forecast.

The statistics are displayed in the form of a table that has the following fields:

Open

• Date - the date the forecast was calculated;

• Time -the time the forecast was calculated;

• Total Items – the number of items participating in the forecast;

• Slow Items – the number of slowly turning positions;

• Stock days – the amount of stock in days;

• Avail % – availability on the shelf in percent;

• Avail ++ – availability change in percent;

• Sales ++ – sales change in money;

• % – percentage sales changes in money;

• Stock -- – stock decrease in money;

• % – percentage stock decrease in money;

• MAPE – mean absolute percentage error.

Forecast statistics can be displayed relative to the following levels:

Open

• SKU - store;

• SKU - region;

• Group - store;

• Group - region.

It is possible to display general statistics press "Full range" checkbox, if previously a forecast was made for all positions.

Open