Automatic Product Copywriting for E-Commerce

TL;DR

This paper presents the deployment of an automatic product copywriting system at JD.com, which generates product descriptions using advanced NLP models, improving key e-commerce metrics significantly.

Contribution

The paper introduces the APCG system integrating transformer-based language models and quality control, deployed in a real-world e-commerce platform for scalable, high-quality copywriting.

Findings

Generated 2.53 million descriptions by Sep 2021

Improved click-through rate by 4.22%

Increased GMV by 213.42% since deployment

Abstract

Product copywriting is a critical component of e-commerce recommendation platforms. It aims to attract users' interest and improve user experience by highlighting product characteristics with textual descriptions. In this paper, we report our experience deploying the proposed Automatic Product Copywriting Generation (APCG) system into the JD.com e-commerce product recommendation platform. It consists of two main components: 1) natural language generation, which is built from a transformer-pointer network and a pre-trained sequence-to-sequence model based on millions of training data from our in-house platform; and 2) copywriting quality control, which is based on both automatic evaluation and human screening. For selected domains, the models are trained and updated daily with the updated training data. In addition, the model is also used as a real-time writing assistant tool on our live broadcast platform. The APCG system has been deployed in JD.com since Feb 2021. By Sep 2021, it has generated 2.53 million product descriptions, and improved the overall averaged click-through rate (CTR) and the Conversion Rate (CVR) by 4.22% and 3.61%, compared to baselines, respectively on a year-on-year basis. The accumulated Gross Merchandise Volume (GMV) made by our system is improved by 213.42%, compared to the number in Feb 2021.