Aligning Hotel Embeddings using Domain Adaptation for Next-Item Recommendation

TL;DR

This paper introduces a domain adaptation method to align hotel embeddings across multiple brands, enhancing next-hotel recommendation accuracy and reducing training time without degrading brand-specific performance.

Contribution

It proposes a simple regularization approach for aligning hotel embeddings across brands using domain adaptation, inspired by cross-lingual embedding techniques.

Findings

Aligned embeddings improve next-hotel prediction accuracy.

The approach reduces training time compared to single-brand models.

Performance is maintained or improved across brands.

Abstract

In online platforms it is often the case to have multiple brands under the same group which may target different customer profiles, or have different domains. For example, in the hospitality domain, Expedia Group has multiple brands like Brand Expedia, Hotels.com and Wotif which have either different traveler profiles or are more relevant in a local context. In this context, learning embeddings for hotels that can be leveraged in recommendation tasks in multiple brands requires to have a common embedding that can be induced using alignment approaches. In the same time, one needs to ensure that this common embedding space does not degrade the performance in any of the brands. In this work we build upon the hotel2vec model and propose a simple regularization approach for aligning hotel embeddings of different brands via domain adaptation. We also explore alignment methods previously used in cross-lingual embeddings to align spaces of different languages. We present results on the task of next-hotel prediction using click sessions from two brands. The results show that the proposed approach can align the two embedding spaces while achieving good performance in both brands. Additionally, with respect to single-brand training we show that the proposed approach can significantly reduce training time and improve the predictive performance.