A Recommendation System Using OLAP Approach

Recommendation Systems (RS) can offer suggestions of items to users. Due to explosive growth of internet, e-commerce, and social networks, RS research has experienced great interest in recent years. Online Analytical Processing (OLAP) and data warehousing technologies have existed for a while and have been popular in many big businesses. In this paper we proposed a new RS system called RS-OLAP which applies the functionalities of OLAP to RS. In particular we aggregate and rollup hierarchical rating data such as users' locations, items' locations and category hierarchies, and incorporate traditional RS algorithms such as Collaborative Filtering (CF) at different levels. In addition, we proposed three other RS algorithms: Top-rated Items in User's Frequent Categories (TIUFC), Pair-wise Association Recommender System (PARS), and RS for spatial items. We also give a framework and prototype for RS-OLAP.