A Transformer-Based Substitute Recommendation Model Incorporating Weakly Supervised Customer Behavior Data

11/04/2022
by   Wenting Ye, et al.
0

The substitute-based recommendation is widely used in E-commerce to provide better alternatives to customers. However, existing research typically uses the customer behavior signals like co-view and view-but-purchase-another to capture the substitute relationship. Despite its intuitive soundness, we find that such an approach might ignore the functionality and characteristics of products. In this paper, we adapt substitute recommendation into language matching problem by taking product title description as model input to consider product functionality. We design a new transformation method to de-noise the signals derived from production data. In addition, we consider multilingual support from the engineering point of view. Our proposed end-to-end transformer-based model achieves both successes from offline and online experiments. The proposed model has been deployed in a large-scale E-commerce website for 11 marketplaces in 6 languages. Our proposed model is demonstrated to increase revenue by 19 based on an online A/B experiment.

READ FULL TEXT
research
05/15/2019

Behavior Sequence Transformer for E-commerce Recommendation in Alibaba

Deep learning based methods have been widely used in industrial recommen...
research
10/25/2019

Data Preprocessing for Evaluation of Recommendation Models in E-Commerce

E-commerce businesses employ recommender models to assist in identifying...
research
05/06/2021

Graph-based Multilingual Product Retrieval in E-commerce Search

Nowadays, with many e-commerce platforms conducting global business, e-c...
research
03/16/2019

Modeling Complementary Products and Customer Preferences with Context Knowledge for Online Recommendation

Modeling item complementariness and user preferences from purchase data ...
research
12/16/2021

Intelligent Online Selling Point Extraction for E-Commerce Recommendation

In the past decade, automatic product description generation for e-comme...
research
09/02/2021

RF-LighGBM: A probabilistic ensemble way to predict customer repurchase behaviour in community e-commerce

It is reported that the number of online payment users in China has reac...
research
08/02/2019

A Hierarchical Bayesian Model for Size Recommendation in Fashion

We introduce a hierarchical Bayesian approach to tackle the challenging ...

Please sign up or login with your details

Forgot password? Click here to reset