AI Scores Personalisation

AI Scores captures and analyses a variety of user activities from different data points and consolidates into a relevant set of user data so you can provide the best personalised experience.

Requirements

In order to use AI Scores you must provide the following:

• Tracking Activities

• Product Feed Data

• Sales History Data (If tracking has been in place for less than 6 months)

Implementation and Flow

Using Api

Ai scores flow using api

Using SDK

Ai scores flow using sdk

The AI Score cluster that the user is assigned to will change as the user performs activities on the site.​

As a cluster may expire during a user session, the version of the user cluster (designated by the generation timestamp) must be aligned with the version of the displayed clusters.

API route to get clusters

You can do a GET request passing the ID of the user to get its clusters :

Cluster API

GET https://collect-eu.attraqt.io/:trackerKey:/users/:idrespositry:/:id:/clusters

Get the clusters of the user with a GET API call

Path Parameters

Name	Type	Description
trackerKey*	string	Your account/tenant trackerKey. Example : f5c09cdc-5c02-4520-8293-b1b12f44f417
idRepository*	string	The idRepository your are using to identify the user. Example : sessionid
id*	string	The id of this user in this idRepository. Example : 5a664160-784e-444c-a6d3-337a2d4af0a6

200

{
   "data": {
     "5ce2a8dbd8c622244f5d1130": {
       "1586436731840": 9,
       "1586307414486": 7
     }
   }
}

For the User details, visit this link:

pageThe User Object

Tracking Response

When implementing tracking the response will look as follows:

Activity response

{ ​
  "profiles": ​{        ​
    "customerid#live1#sessionid#a4c2386e-b19": ​{ ​
      "clusters": ​{
        "5f11b72aa6b7e52e94b8a6cf": ​{ ​ // Algorithm Id
          "1634504597142": 2, // key: Timestamp, value: Cluster Number for profile
          "1634591034702": 10 ​
        } ​
      } ​
    } ​
  } 
}

Cluster endpoint response

{
   "data": {
     "5ce2a8dbd8c622244f5d1130": {
       "1586436731840": 9,
       "1586307414486": 7
     }
   }
}

Versioning in Fredhopper​

AI Scores are versioned to prevent shopper/cluster mismatches when a new update has been processed.

Clusters object returned by activities or cluster get method responds with two versions and provides the user's cluster value for each of these​

When the front-end generates the query string request to Fredhopper, it should use the cluster ID for the model version that matches that in the local ‘current model version’ variable​

A new display field will be enabled on the published endpoint which the front-end can use to determine the current cluster value (Epoch timestamp) that is loaded and should be used.

Fredhopper Versioning

Considerations

When looking to implement AI Scores, keep the following in mind:

• What sections of the site do you want AI Scores to power?​

• Where do you plan to use AI Scoring? Website, app or both​?

• Implementing AI Scores will affect page caching, if this is a concern:​

  • do all pages need to have AI Scores?​

  • do all users need to have AI Scores?