Cluster-based Contextual Recommendations

In this work, we address the problem of contextual recommendations by exploiting the concept of fault-tolerant subspace clustering. Specifically, we pre-partition users that have similarly rated subsets of data items into clusters and associate with each cluster a context situation. Context is defined as any internally stored information that can be used to characterize the data per se. Then, given a query context, we identify the clusters with the most similar context, and use their members for making suggestions in a collaborative filtering manner.

• Type: Journal
• Year: 2016
• Where: EDBT
• Keywords: Database, EDBT 2016