Biclustering Based on FCA and Partition Pattern Structures for Recommendation Systems

Nyoman Juniarta (1) , Victor Codocedo (2) , Miguel Couceiro (1) , Amedeo Napoli (1)

1 ORPAILLEUR - Knowledge representation, reasonning
2 DM2L - Data Mining and Machine Learning

This paper focuses on item recommendation for visitors in a museum within the framework of European Project CrossCult about cultural heritage. We present a theoretical research work about recommendation using biclustering. Our approach is based on biclustering using FCA and partition pattern structures. First, we recall a previous method of recommendation based on constant-column biclusters. Then, we propose an alternative approach that incorporates an order information and that uses coherent-evolution-on-columns biclusters. This alternative approach shares some common features with sequential pattern mining. Finally, given a dataset of visitor trajectories, we indicate how these approaches can be used to build a collaborative recommendation strategy.

Mots clés: biclustering; FCA; pattern structures; recommendation

Domaines: Informatique [cs]

Nyoman Juniarta, Victor Codocedo, Miguel Couceiro, Amedeo Napoli. Biclustering Based on FCA and Partition Pattern Structures for Recommendation Systems. NFMCP 2018 - 7th International Workshop on New Frontiers in Mining Complex Patterns, Sep 2018, Dublin, Ireland. ⟨hal-01889384⟩