J-Recs: Principled and Scalable Recommendation Justification

TL;DR

J-Recs is a scalable, model-agnostic method for generating diverse, concise, and effective post-hoc justifications for recommendations, improving user satisfaction and matching preferences more accurately.

Contribution

We introduce J-Recs, a novel graph-based approach that produces diverse, concise justifications using multiple data types, addressing limitations of existing post-hoc methods.

Findings

J-Recs generates justifications that match user preferences up to 20% more accurately.

The method produces diverse and concise justifications across different data types.

J-Recs is efficient and applicable to any recommendation algorithm.

Abstract

Online recommendation is an essential functionality across a variety of services, including e-commerce and video streaming, where items to buy, watch, or read are suggested to users. Justifying recommendations, i.e., explaining why a user might like the recommended item, has been shown to improve user satisfaction and persuasiveness of the recommendation. In this paper, we develop a method for generating post-hoc justifications that can be applied to the output of any recommendation algorithm. Existing post-hoc methods are often limited in providing diverse justifications, as they either use only one of many available types of input data, or rely on the predefined templates. We address these limitations of earlier approaches by developing J-Recs, a method for producing concise and diverse justifications. J-Recs is a recommendation model-agnostic method that generates diverse justifications based on various types of product and user data (e.g., purchase history and product attributes). The challenge of jointly processing multiple types of data is addressed by designing a principled graph-based approach for justification generation. In addition to theoretical analysis, we present an extensive evaluation on synthetic and real-world data. Our results show that J-Recs satisfies desirable properties of justifications, and efficiently produces effective justifications, matching user preferences up to 20% more accurately than baselines.