Infrequent Item-to-Item Recommendation via Invariant Random Fields

Abstract

Web recommendation services bear great importance in e-commerce and social media, as they aid the user in navigating through the items that are most relevant to her needs. In a typical web site, long history of previous activities or purchases by the user is rarely available. Hence in most cases, recommenders propose items that are similar to the most recent ones viewed in the current user session. The corresponding task is called session based item-to-item recommendation. Generating item-to-item recommendations by “people who viewed this, also viewed” lists works fine for popular items. These recommender systems rely on item-to-item similarities and item-to-item transitions for building next-item recommendations. However, the performance of these methods deteriorates for rare (i.e., infrequent) items with short transaction history. Another difficulty is the cold-start problem, items that recently appeared and had no time yet to accumulate a sufficient number of transactions. In this paper, we describe a probabilistic similarity model based on Random Fields to approximate item-to-item transition probabilities. We give a generative model for the item interactions based on arbitrary distance measures over the items including explicit, implicit ratings and external metadata. We reach significant gains in particular for recommending items that follow rare items. Our experiments on various publicly available data sets show that our new model outperforms both simple similarity baseline methods and recent item-to-item recommenders, under several different performance metrics.