ℹ️ Internal article. This action is an internal CRS operations job and is not intended for customer use. Contact support if the functionality is of interest to you.
Trains an AI demand model on sales history in the BI database, forecasts demand over the lead-time and safety-stock window, applies purchase min/max constraints, and writes restock suggestions to ml_restock_suggestions for Power BI without creating purchase orders.
The action is an internal operations job that runs on a schedule at CRS. It requires administrator rights and direct database access and is not part of a normal customer setup.
Parameter | Explanation |
| Connection string to the BI/Power BI database that holds the sales history and receives the restock suggestions. |
| Estimated supplier lead time in days from order to delivery, used as part of the forecast horizon. |
| Minimum number of historical sales rows a SKU must have before it is eligible for a restock suggestion. |
| Optional organizational unit id to run for a single OU; leave empty to process every OU that has enough data. |
| Half-life in days for the recency weight applied during training; set to 0 to weight all rows equally. |
| Safety stock buffer in days added on top of the lead time to set the total forecast horizon. |
| Optional order date (yyyy-MM-dd) the suggestions are calculated for; defaults to today. |
| How many months of sales history to train the demand model on. |
See also the overview SyncTool – actions.
