Predicting Location-Based Sequential Purchasing Events by Using Spatial, Temporal, and Social Patterns

Location-based sequential event prediction is an interesting problem with many real-world applications. For example, knowing when and where people will use certain kinds of services could enable the development of robust anticipatory systems. A key to this problem is in understanding the nature of the process from which sequential data arises. Usually, human behavior exhibits distinct spatial, temporal, and social patterns. The authors examine three kinds of patterns extracted from sequential purchasing events and propose a novel model that captures contextual dependencies in spatial sequence, customers' temporal preferences, and social influence via an implicit network. Their model outperforms existing models based on evaluations using a real-world dataset of smartcard transaction records from a large educational institution with 13,753 students during a 10-month time period.