Discovering Useful Compact Sets of Sequential Rules in a Long Sequence

Erwan Bourrand (1, 2) , Luis Galárraga (1) , Esther Galbrun (3) , Elisa Fromont (1, 4) , Alexandre Termier (1)

1 LACODAM - Large Scale Collaborative Data Mining
2 AdvisorSLA [Massy]
3 University of Eastern Finland
4 IUF - Institut universitaire de France

We are interested in understanding the underlying generation process for long sequences of symbolic events. To do so, we propose COSSU, an algorithm to mine small and meaningful sets of sequential rules. The rules are selected using an MDL-inspired criterion that favors compactness and relies on a novel rule-based encoding scheme for sequences. Our evaluation shows that COSSU can successfully retrieve relevant sets of closed sequential rules from a long sequence. Such rules constitute an interpretable model that exhibits competitive accuracy for the tasks of next-element prediction and classification.

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Erwan Bourrand, Luis Galárraga, Esther Galbrun, Elisa Fromont, Alexandre Termier. Discovering Useful Compact Sets of Sequential Rules in a Long Sequence. ICTAI 2021 - 33rd IEEE International Conference on Tools with Artificial Intelligence, Nov 2021, Virtual, United States. pp.1-5. ⟨hal-03494520⟩