aexol-studio / newsletter_samarite

Recommendation System for samarite (newsletter)

  • Public
  • 77 runs
  • CPU
Iterate in playground

Input

*secret

A secret has its value redacted after being sent to the model.

Samarite API URL

*secret

A secret has its value redacted after being sent to the model.

Samarite API Login

*secret

A secret has its value redacted after being sent to the model.

Samarite API Password

integer

Number of last orders to retrieve, more than 10000 and less than 200000

Default: 0

string
Shift + Return to add a new line

Start date for the data retrieval e.g. 2024-01-01T07:25:18.724Z

string
Shift + Return to add a new line

End date for the data retrieval e.g. 2024-03-01T07:25:18.724Z (the period should be at least one week)

string

Product name

string
Shift + Return to add a new line

Custom product name

string

Prediction type

Default: "rfm-score"

boolean

Whether to show the evaluation metrics

Default: false

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on CPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

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.