Computational techniques for more accurate and diverse recommendations.

Abstract

Recommender systems are becoming an increasingly important research area due to the growing demand for personalized recommendations. The volume of information available to each user and the number of products carried in e-commerce marketplaces have grown tremendously. Thus, recommender systems are needed to help individual users find the most relevant items from an enormous number of choices and eventually increase sales by exposing users to what they may like, but may not have considered otherwise. Despite significant progress in developing new recommendation techniques within both industry and academia, most research, to date, has focused on improving recommendation accuracy (i.e., the accuracy with which the recommender system predicts users` ratings for items they have not yet rated). While recommendation accuracy is undoubtedly important, there is a growing understanding that accuracy does not always imply usefulness to users. Therefore, in addition to investigating the accuracy of recommendations, my dissertation also considers the diversity of recommendations as another important aspect of recommendation quality and explores the relationship between accuracy and diversity. The diversity of recommendations can be expressed by the number of unique items recommended across all users, which reflects the ability of recommender systems to go beyond the obvious, best-selling items, and to generate more idiosyncratic, personalized, and long-tail recommendations. This dissertation presents four studies which propose new recommendation approaches that can improve accuracy and diversity. The first study enhances traditional recommendation algorithms by augmenting them with multi-criteria rating information for more accurate recommendations. The second study applies heuristic-based ranking approaches for more diverse recommendations. The third study develops more sophisticated optimization approaches for direct diversity maximization. The fourth study explores the possible combinations of the two types of approaches - incorporation of multi-criteria rating information and the use of different ranking methods - as a way to generate recommendations that are both more accurate and more diverse. The new recommendation approaches proposed in this dissertation enrich the body of knowledge on recommender systems by extending single-rating recommendation problems to address multi-criteria recommendation problems and exploring new ways to tackle the accuracy-diversity tradeoff issue. Individual users and online content providers will also benefit from the proposed approaches, in that each user will find more relevant and personalized items from more accurate and diverse recommendations provided by recommender systems. These approaches could potentially lead to increased loyalty and sales, thus, benefiting the providers as well.