aexol-studio / newsletter_samarite

Recommendation System for samarite (newsletter)

  • Public
  • 76 runs

Recommendations: 1. Don’t use both num_last_orders and start_date/end_date parameters at the same time. If you use num_last_orders parameter, leave start_date and end_date empty. Otherwise, if you use start_date and end_date parameters, leave num_last_orders with 0. 2. Make sure the date is in the correct format (ISO 8601). 3. Provided num_last_orders parameter must be between 10000 and, 200000. 4. Minimum time range is 1 week. 5. If product parameter is set to ALL, the model will predict for all products. 6. If product are not in the dataset or only in a small amount of orders, the model will return an error. 7. If you want to enter a custom product name, set product to CUSTOM and enter your product name in the custom_product parameter. 8. Provided more orders or longer time range will result in better predictions.