Web-to-Voice Transfer for Product Recommendation on Voice

Abstract

While product recommendation algorithms on the Web are wellsupported by a vast amount of interaction data, the same is not true on Voice. A promising approach to mitigate the issue is transfer learning, i.e., transferring the knowledge of customers' shopping behaviors learned from their shopping activities on the Web to Voice. Such a Web-to-Voice transfer is challenging due to customers' distinct shopping behaviors on Voice: customers are inclined to purchase more low-consideration products and are more likely to purchase certain products repeatedly. This paper presents TransV, a novel Web-to-Voice neural transfer network that allows for effective transfer of customers' shopping patterns from the Web to Voice, while taking into account customers' distinct purchase patterns on Voice. Our method extends the state-of-the-art self-attention neural architecture with a multi-level tri-factorization neural component, which allows to explicitly capture the similarity and dissimilarity of customers' shopping patterns on the Web and Voice. To model repeated purchases, TransV adopts a recency-based copy mechanism that considers the impact of the recency of historical purchases on customers' behavior of repeated purchases. Extensive validation on multiple real-world datasets, including two cross-platform datasets from Amazon.com and Amazon Alexa, shows that our method is able to improve voice-based recommendation substantially by 26.8% as compared with non-transfer learning methods. CCS CONCEPTS • Information systems → Recommender systems; • Computing methodologies → Transfer learning; Neural networks.

Towards Building Voice-based Conversational Recommender Systems: Datasets, Potential Solutions and Prospects

“…As a result, there is currently no available public dataset for research on VCRSs. Besides, another work [44], though involving voice-based recommendation, aims to transfer customers' shopping patterns from the web to the voice platform, thus being different from our goal of CRSs directly on voices.…”

Effects of Feature-Based Explanation and Its Output Modality on User Satisfaction With Service Recommender Systems

“…Kraus et al (2019) surveyed a focus group of e-commerce experts on their experiences in the voice and web commerce recommenders and found that convenience has a larger effect in the voice commerce. Zhang and Yang (2020) considered the shopping behaviors on vocal as distinct from visual when they designed a network-based recommender system, which include the tendency to consume more lowconsideration products and purchase repeatedly. However, the effects of the output modality of recommendation explanation on user experience have rarely been investigated.…”