Clustering
Clustering makes it possible to group users and items into a specified number of clusters. For finding cluster, there are three different algorithms that can be used:
embedding
with item clusters from the trained machine-learning model and users assigned to the most connected cluster,plsa
, Probabilistic Latent Semantic Analysis run separately, andmodularity
, network-based modularity optimizationrun separately.
embedding
is the fastest method since it uses the trained machine-learning model.