Using the Context of User Feedback in Recommender Systems

TL;DR

This paper explores how incorporating presentation context improves implicit feedback-based recommendations in small to medium e-commerce, validated through real user data and offline experiments.

Contribution

It introduces a model of relevant contextual features, proposes methods to leverage them, and provides a new dataset for e-commerce user feedback analysis.

Findings

Leveraging presentation context enhances purchase prediction accuracy.

Context-aware recommendation models outperform context-agnostic ones.

Real user data confirms the importance of context in recommendation effectiveness.

Abstract

Our work is generally focused on recommending for small or medium-sized e-commerce portals, where explicit feedback is absent and thus the usage of implicit feedback is necessary. Nonetheless, for some implicit feedback features, the presentation context may be of high importance. In this paper, we present a model of relevant contextual features affecting user feedback, propose methods leveraging those features, publish a dataset of real e-commerce users containing multiple user feedback indicators as well as its context and finally present results of purchase prediction and recommendation experiments. Off-line experiments with real users of a Czech travel agency website corroborated the importance of leveraging presentation context in both purchase prediction and recommendation tasks.