Metrics
>
Laboratory

LABORATORY

Sections:

Metrics - group of metrics on Datawiz BI service

There is a list of metrics of the group "Laboratory".

Access to viewing metrics according to the user's role is determined by the administrator. To expand access, contact your administrator.

 

the column that is created to get feedback (rating and/or recommendations) from users and improve new reports following the current needs of retailers.

Loss of sales, which arose because the products were not sold for a certain number of days.

the difference between loss of sales ML metrics for the selected and previous periods.

the difference between loss of sales ML metrics for the selected and previous periods, calculated as a percentage.

the percentage of lost sales ML from total lost sales ML for the selected period.

Loss of sales which arose because the products were not sold as the stocks were null.

the difference between loss of sales when stocks are null ML metrics for the selected and previous periods.

the difference between loss of sales when stocks are null ML metrics for the selected and previous periods, calculated as a percentage.

the difference between the predicted sales at the optimal price and the predicted sales at the current price of all products included in the recommendations for 30 days.

the total qty of sales that can be predictably received by accepting all the recommendations displayed in the report.

the average sales on similar stores for the selected period.

Note! Stores where the algorithm found similar sales for the selected period are called similar.

the difference between predicted sales (day) metrics, calculated as a percentage.

the sales that can be predictably received per day by accepting all the recommendations displayed in the report.

the percentage of sales losses ML from the sales for the selected period.

the amount of cash proceeds from the sale of products calculated using the ML algorithm for the selected period.

the probable sales qty that could have been in the selected period in the absence of problems in the store.

the difference between loss of sales Qty ML metrics for the selected and previous periods.

the difference between loss of sales Qty ML metrics for the selected and previous periods, calculated as a percentage.

the percentage of lost sales qty ML from total lost sales Qty ML for the selected period.

loss of sales which arose because of absence of the stocks.

the difference between loss of sales qty when stocks are null ML metrics for the selected and previous periods.

the difference between loss of sales qty when stocks are null ML metrics for the selected and previous periods, calculated as a percentage.

the total qty of sales that can be predictably received per day by accepting all the recommendations displayed in the report.

the difference between the predicted sales at the optimal price and the predicted sales at the current price of all products included in the recommendations for 30 days.

the difference between predicted sales qty (day), calculated as a percentage.

the total qty of sales that can be predictably received by accepting all the recommendations displayed on the report.

the average sales qty on similar stores for the selected period.

Note! Stores where the algorithm found similar sales for the selected period are called similar.

the percentage of losses of sales Qty ML from total sales qty for the selected period.

the qty of natural units of products/categories/brands sold during the selected period, calculated using the ML algorithm.

loss of profit, which arose because the products were not sold for a certain number of days.

the difference between loss of profit ML metrics for the selected and previous periods.

the difference between loss of profit ML metrics for the selected and previous periods, calculated as a percentage.

the percentage of lost profit share ML from total lost profit ML for the selected period.

the percentage of profit losses ML from total profit ML for the selected period.

loss of profit which arose because the stocks were null.

the difference between loss of profit when stocks are null ML metrics  for the selected and previous periods.

the difference between loss of profit when stocks are null ML metrics for the selected and previous periods, calculated as a percentage.

the difference between the predicted profit at the optimal price and the predicted profit at the current price of all products included in the recommendations for 30 days.

the difference between predicted profit (Day) metrics, calculated as a percentage.

the profit that can be predictably received per day by accepting all the recommendations displayed on the report.

the total profit that can be predictably received by accepting all the recommendations displayed in the report.

the average profit on similar stores for the selected period.

Note! Stores where the algorithm found similar sales for the selected period are called similar.

the difference between the monetary proceeds from the product sales (turns) and the product primecost calculated by the ML algorithm for the selected period.

the price that, according to previous product sales, will bring to store the largest amount of profit of this product.

the difference between optimal price metrics, calculated as a percentage.

the margin that can be predictably received by accepting all the recommendations displayed in the report.

the qty of days during the selected period when the product was not sold.

the difference between qty of losing days ML metrics.

the difference between qty of losing days ML metrics, calculated as a percentage.

qty of days during the selected period with losses which arose because the stocks were null.

the difference between qty of losing sales when stocks are null ML metrics for the selected and previous periods.

the difference between qty of losing sales days when stocks are null ML, for the selected and previous periods, calculated as a percentage.

Qty of products for which lost sales were found using the ML algorithm.

The number of products for which the algorithm generated recommended optimal prices for the current period

The number of stores for which the algorithm generated recommended optimal prices for the current period

The date of acceptance by the user of the optimal price recommendation for the product.

The number of products for which optimal price recommendations have been accepted for the current period.

The number of stores for which optimal price recommendations have been accepted for the current period.

accounting price of the product while acceptance of the recommendation.

primecost of the product while acceptance of the recommendation.