Collaborative Filtering via Additive Ordinal Regression

Accurately predicting user preferences/ratings over items are crucial for many Internet applications, e.g., recommender systems, online advertising. In current main-stream algorithms regarding the rating prediction problem, discrete rating scores are often viewed as either numerical values or(nominal) categorical labels. Practically, viewing user rating scores as numerical values or categorical labels cannot precisely reflect the exact degree of user preferences. It is expected that for each user, the quantitative distance/scale between any pair of adjacent rating scores could be different. In this paper, we propose a new ordinal regression approach. We view ordered preference scores in an additive way, where we are able to model users» internal rating patterns. Specifically, we model and learn the quantitative distances/scales between any pair of adjacent rating scores. In this way, we can generate a mapping from users» assigned discrete rating scores to the exact magnitude/degree of user preferences for items. In the application of rating prediction, we combine our newly proposed ordinal regression method with matrix factorization, forming a new ordinal matrix factorization method. Through extensive experiments on benchmark datasets, we show that our method significantly outperforms existing ordinal methods, as well as other popular collaborative filtering methods in terms of the rating prediction accuracy.