Lead Time Prediction

Lead Time prediction is the process of forecasting the future lead time for your catalogue items. It is based on historical data for purchase orders, and uses machine learning algorithms to provide you with accurate predictions.

Lead Time Prediction returns the estimated lead time in days.

Requesting a Lead Time Prediction

To request a lead time prediction, you need to have a collection with historical data for purchase orders on Mantissa. You can create a collection and upload your data following instructions in the Collection section.

Once you have uploaded your purchase orders data, you can request a lead time prediction by sending a POST request to the invocation endpoint, with lead-time-prediction as invocationType. See more at Invoke Mantissa.

You can customize your lead time prediction by specifying the following parameters in the request body:

• horizon: the number of periods for which you want to predict the lead time;
• start_date: the first date for which you want to generate forecasts;
• granularity: the reference period for which the forecasts are to be calculated;
• aggregation: the taxonomy level for which to receive forecasts.

For details on the parameters, look at the Customizing Invocations section.

Interpreting the Lead Time Prediction Results

The results of a lead time prediction request will provide you with the estimated lead time for each item in your inventory. The lead time is forecasted for the granularity and aggregation level you selected, starting from the starting date you specified, for the number of periods you requested.

Here is provided an example for a Lead Time Prediction.

Suppose you have three items in your inventory: item1, item2, and item3. Their taxonomy is as follows:

• item1: classification1, family1;
• item2: classification1, family1;
• item3: classification2, family2.

Example 1

You request a lead time prediction with parameters:

• horizon: 3;
• start_date: 2022-01-31;
• granularity: M;
• aggregation: item.

The output, in json format, will be:

[
  {
    "ItemCode": "item1",
    "OrderDate": "2022-01-31",
    "LeadTime": 2
  },
  {
    "ItemCode": "item1",
    "OrderDate": "2022-02-28",
    "LeadTime": 4
  },
  {
    "ItemCode": "item1",
    "OrderDate": "2022-03-31",
    "LeadTime": 3
  },
  {
    "ItemCode": "item2",
    "OrderDate": "2022-01-31",
    "LeadTime": 13
  },
  {
    "ItemCode": "item2",
    "OrderDate": "2022-02-28",
    "LeadTime": 12
  },
  {
    "ItemCode": "item2",
    "OrderDate": "2022-03-31",
    "LeadTime": 19
  },
  {
    "ItemCode": "item3",
    "OrderDate": "2022-01-31",
    "LeadTime": 8
  },
  {
    "ItemCode": "item3",
    "OrderDate": "2022-02-28",
    "LeadTime": 12
  },
  {
    "ItemCode": "item3",
    "OrderDate": "2022-03-31",
    "LeadTime": 9
  }
]

The numbers associated to each date represent the predicted lead time (in days) for the item.

Example 2

You request a lead time prediction with parameters:

• horizon: 2;
• start_date: 2022-01-30;
• granularity: W;
• aggregation: family.

The output, in json format, will be:

[
  {
    "ItemFamily": "family1",
    "OrderDate": "2022-01-30",
    "Quantity": 7
  },
  {
    "ItemFamily": "family1",
    "OrderDate": "2022-02-28",
    "Quantity": 8
  },
  {
    "ItemFamily": "family2",
    "OrderDate": "2022-01-30",
    "Quantity": 8
  },
  {
    "ItemFamily": "family2",
    "OrderDate": "2022-02-28",
    "Quantity": 12
  }
]