Recommendations
This model provides a recommendation of objects to the user based on their activity. Qualetics Data Streaming is required as this model is dependent on data for fine-tuning the recommendation engine to your organization's data.
The data required for providing recommendations will be gathered from the user activity streamed as part of the events and the Object data for each event. Please refer to the instructions in the Object configuration to enable indexing on the entities that need to be included in the recommendation engine.
This model is best suited when a list of recommendations need to be provided to the user based on their activity over the past 7 Days.
The results can be fine tuned based by limiting the recommendations to be gathered from specific actions performed by the user. For example - In an ecommerce application, the recommendations can be based on only those products that the user has purchased in the past and other actions such as Add to Cart, Comparison, Saving to Wish List can be ignored. If no Action name is provided in the input parameters, all actions will be considered as candidates for recommendation.
Additionally, the results can be further finetuned based on object features such as Title, Description, Specifications etc so that only data present in those fields will be considered for performing a comparison search.
Note: Data Streaming integration is required for this model. Please complete the integration setup, verify the data connection and ensure that the streaming is Live before using this model.
Parameter Name | Parameter Type | Required |
|---|---|---|
userid | Text | Yes |
object type | Text | Yes |
feature name | Text | Yes |
action name | Text | |
Rest API Input Example
Parameter Name | Parameter Type | Info |
|---|---|---|
recommendations | JSON Array | Contains an array of JSON Objects with each object containing the id of the object, result based on the feature specified and the similarity score indicating the match with the user's previous activity |
actor | string | ID of the actor |
Rest API Output Example
Every model execution output consists of the following standard output parameters
- input
- The input string required for the model to extract the categories
- original input
- This is the input provided to the first step in model which is retained across multiple steps in a Data Machine workflow.
- final result
- The result of the model executed in the final step of the Data Machine workflow
- sessionid
- A unique session id that is generated for every execution of a Data Machine which can be used to retain results across multiple sessions
- status
- The result of the Data Machine execution. If all of the steps in a sequence are successfully executed, a value of "Completed" is provided. If the execution is interrupted at any point, a value of "Terminated" is provided with the reason for Termination.
