Generalized theme dictionary models for association pattern discovery

Abstract

Discovering association patterns of items from a collection of baskets composed of different items is an important problem in various fields. Assuming that each basket is composed of themes of items randomly sampled from a theme dictionary, the theme dictionary model provides a general framework to achieve efficient association pattern discovery with statistical inference. This paper extends the original theme dictionary model by allowing more than one category of items in a basket and only presence/absence of items is observed for each basket with all quantitative information missing. The extended models can solve a larger range of practical problems that cannot be handled by the original theme dictionary model. Both simulation studies and real data applications confirm the superiority of the proposed methods over the existing ones.