Paper ID: FSDM1863
Presenter: Belgin Ergenc, Izmir Institute of Technology, Turkey
Title of Presentation: Dynamic Itemset Mining under Multiple Support Thresholds
Abstract of Presentation: Handling dynamic aspect of databases and multiple support threshold requirements of items are two important challenges of frequent itemset mining algorithms. Frequent itemsets should be updated when the database is updated without re-running the mining algorithm. At the same time, frequent itemset mining algorithm should consider different support thresholds in order not to cause rare item problem. Existing dynamic itemset mining algorithms are devised for single support threshold whereas multiple support threshold algorithms assume that the databases are static. This paper focuses on dynamic update problem of frequent itemsets under MIS (Multiple Item Support) thresholds and introduces Dynamic MIS algorithm. It is i) tree based and scans the database once, ii) considers multiple support thresholds, and iii) handles increments of additions, additions with new items and deletions. Proposed algorithm is compared to CFP-Growth++ and findings are; in dynamic database 1) Dynamic MIS performs better than CFP-Growth++ since it runs only on increments and 2) Dynamic MIS can achieve speed-up of 56 times against CFP-Growth++.