Collaborative Filtering & Mobile Recommender Systems

Collaborative Filtering is Not Enough? Experiments with a Mixed-Model Recommender for Leisure Activities
Nicolas Ducheneaut, Kurt Partridge, Qingfeng Huang, Bob Price, Michael Roberts, Ed H. Chi, Victoria Bellotti, Bo Begole

Collaborative filtering (CF) is at the heart of most successful recommender systems nowadays. While this technique often provides useful recommendations, conventional systems also ignore data that could potentially be used to refine and adjust recommendations based on a user’s context and preferences. The problem is particularly acute with mobile systems where information delivery often needs to be contextualized. Past research has also shown that combining CF with other techniques often improves the quality of recommendations. In this paper, we present results from an experiment assessing user satisfaction with recommendations for leisure activities that are obtained from different combinations of these techniques. We show that the most effective mix is highly dependent on a user’s familiarity with a geographical area and discuss the implications of our findings for future research.

Enhancing Mobile Recommender Systems with Activity Inference
Kurt Partridge, Bob Price

Today’s mobile leisure guide systems give their users unprecedented help in finding places of interest. However, the process still requires significant user interaction, specifying preferences and navigating through lists. We argue that this interaction, while effective when used properly, is an obstacle for users trying to learn these systems. Furthermore, ad-placement systems, which functionally resemble recommender systems, must rely on other sources of information to automatically infer the user’s preferences and interests. In this paper, we describe how automatically infer a user’s high-level activity to better support recommendations. Activity is determined by interpreting a combination of current sensor data, models generated from historical sensor data, and priors from a large time-use study. We present an initial user study that shows prediction accuracy improvements from 62% to over 77%, and a discussion of the challenges of integrating activity representations into a user model.