Supporting mobile decision making with association rules and multi-layered caching

We describe a methodology and a prototype implementation of an online analytical processing system for mobile devices. The system guides the user to narrow down the search space using association rules. We also describe multi-layered caching techniques to improve performance and increase system utilization even in the presence of disconnections. The system is built using a three-tier architecture comprising of a data warehouse, a middle-tier server, and client mobile devices. Finally we conducted a series of simulation experiments to evaluate the performance of our association rule-based system and the multi-layered caching.