Step 6: User-Clustering - Run Clustering, View Trade-Off, Choose Cluster Count

Step 6.1: Cluster Users

This API call executes the clustering using the latent factors/embeddings trained in the recommender. You select the minimum and the maximum number of user-clusters to be tested for their MSE (Mean Square Error). This will be used to choose the optimal number of user-clusters for your organisation.

For more information, please refer to the API documentation.

Step 6.2: Trade-Off User Chart

This API call gets the mean squared error for each user-cluster count between the specified min and max.

For more information, please refer to the API documentation.

Step 6.3: Choosing User Cluster Count based on MSE Results

Once you have looked at the clusters' MSE results, you can decide how many item clusters are optimal. Usually, the number of clusters where the drop-off in MSE elbows is selected.

For more information, please refer to the API documentation.