New Vector-Space Embeddings For Recommender Systems

In this work, we propose a novel recommender system model based on a technology commonly used in natural language processing called word vector embedding. In this technology, a word is represented by a vector that is embedded in an n-dimensional space. The distance between two vectors expresses the level of similarity/dissimilarity of their underlying words. Since item similarities and user similarities are the basis of designing a successful collaborative filtering, vector embedding seems to be a good candidate. As opposed to words, we propose a vector embedding approach for learning vectors for items and users. There have been very few recent applications of vector embeddings in recommender systems, but they have limitations in the type of formulations that are applicable. We propose a novel vector embedding that is versatile, in the sense that it is applicable for the prediction of ratings and for the recommendation of top items that are likely to appeal to users. It could also possibly take into account content-based features and demographic information. The approach is a simple relaxation algorithm that optimizes an objective function, defined based on target users', items' or joint user-item's similarities in their respective vector spaces. The proposed approach is evaluated using real life datasets such as "MovieLens", "ModCloth", "Amazon: Magazine_Subscriptions" and "Online Retail". The obtained results are compared with some of the leading benchmark methods, and they show a competitive performance.