Use this CSV file as a template to set up your import action. Every time you run a forecast action, this configuration imports the results into your forecast results module.
You can use the module to compare the different sets of results against each other.
To create the import action:
(1) Use Excel to create a new CSV file.
(2) Use the CSV file to create your column headers.
(3) Add column headers for the following data items, exactly as shown below:
Note: Use this column to map the different sets of predictions from each forecast action.
Note: P1, P2, and P3 represent the three prediction quantiles you can apply to your forecast.
(4) You can also add the following columns if you want to analyze seasonality and trends:
We recommend you include these column headers so you can clearly identify patterns over time.
(a) Seasonality helps you spot demand spikes for regular time intervals. For example, if your daily data has a weekly seasonality pattern, you can view this with the data in the PlanIQ_Seasonality_Weekly line item.
(b) You can use PlanIQ_Trend_Quarterly and PlanIQ_Trend_Yearly to discover trends over a broader period of time.
(c) Trend is calculated by quarter or year.
(d) It's useful to view the current trendline as well as spot changes in a trend.
(e) The quarterly or yearly trends only display if there's enough data to calculate them.
(5) In the CSV file, add a placeholder entry for the timestamp column, and add an actual entry for the item_id column.
Keep the other columns empty. See the example below (scroll across to see the full table):
|2021-01-01||[Insert one of your actual items or SKUs in this column]|
(6) In the module, select Data>Import to import the CSV file.
(7) Select Upload New File... and upload the CSV file.
(8) In the Set Default File dropdown, select either Admins Only, or Everyone.
This makes sure the import runs correctly
(9) Select Next.
(1) Select the Mapping tab and map the source columns to the target columns.
|Column 1: timestamp||Time|
|Column 2: item_id||Item_id|
|Column 3: forecast_action||[If you decide to map the forecast action, map it to the forecast_action_name dimension in your forecast results module.]|
|Column 4: P1|
|Column 5: P2|
|Column 6: P3|
|Column 7: PlanIQ_Seasonality_Weekly|
|Column 8: PlanIQ_Seasonality_Bi_weekly|
|Column 9: PlanIQ_Seasonality_Monthly|
|Column 10: PlanIQ_Seasonality_Quarterly|
|Column 11: PlanIQ_Seasonality_Yearly|
|Column 12: PlanIQ_Trend_Quarterly|
|Column 13: PlanIQ_Trend_Yearly|
(2) In the Mapping tab, select Only update imported cells.
Optional: If you only want to map some or none of the seasonality and trend analysis columns, you need to do manual mapping. In Forecast results line items:
(4) Select Map items manually.
Then you can carry out partial mapping, and just map the columns you need for your forecast.
(5) Select the Time tab and select Dates.
Ensure the date format is Y-M-D.
(6) Select Run import.
Now you're ready to use PlanIQ.