Improved Metric-Based Recommender by Historical Interactions

Abstract

A remarkable success in recommendations has been achieved by using methods based on metric learning, especially in digital marketing. However, the existing methods do not consider the relative preferences among items that users like. To overcome this issue, we propose an improved recommender model. First, the model analyses the user-item bipartite graph from historical interactions, and collects user-item similarities based on the topological features from this graph. Then, similar to other metric-based methods, both users and items are embedded as latent positions in a low-dimensional space, where users’ preferences on items are modelled as distances. Thus, we propose an improved metric-based recommender, i.e. the Graph Embedded Metric Factorisation recommender, under the assumptions that (1) the distance between a target user and an interacted-with item is determined by their topological similarity, and (2) for a target user, non-interacted items are located farther away than interacted-with ones. Comprehensive experiments on three practical datasets were implemented. Empirical results indicate that our improved recommender outperforms current state-of-the-art methods when making personalised recommendations based on users’ implicit feedback.