Machine Learning-Based Customer Churn Risk Prediction for Live Streaming e-Commerce

Xiangchen Meng, Runy Li, Qianqian Song

2025

Abstract

As an emerging sales model, live streaming e-commerce has developed rapidly in recent years and has rapidly attracted many consumers. According to the data, the scale of the live broadcast e-commerce market in 2020 has reached more than 900 billion yuan. This impressive number has attracted many e-commerce companies, who have begun to explore and integrate into this live streaming sales field. For example, at 8 p.m. on March 20, 2020, Taobao Live's top streamer Wei Ya sold 560 million items during the live broadcast, attracting more than 700 million viewers, which significantly demonstrates the potential of live streaming to bring goods. In order to further promote the development of live e-commerce, Taobao Live announced on June 15, 2020 that it would invest a large amount of traffic resources to support live streamers on Taobao within a year, and launched a "new infrastructure" plan to upgrade Taobao's content ecosystem. Although live-streaming e-commerce has brought huge business opportunities, its rapid development has also raised some questions. First of all, the promotional strategies in the live broadcast room, such as "routines", "low prices" and "coupons", make it difficult for consumers to recognize. Secondly, the products promoted by the anchor may not match the actual needs of consumers. What's more, livestreaming e-commerce may be at risk of losing customers. To identify and predict this potential risk of churn, big data and machine learning techniques can be leveraged for analysis. Through these technologies, it is possible to gain insight into consumer behavior patterns and preferences, so that we can better anticipate and respond to possible market changes.

Paper Citation

in Harvard Style

Meng X., Li R. and Song Q. (2025). Machine Learning-Based Customer Churn Risk Prediction for Live Streaming e-Commerce. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 1: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 283-288. DOI: 10.5220/0013540000004664

in Bibtex Style

@conference{incoft25,
author={Xiangchen Meng and Runy Li and Qianqian Song},
title={Machine Learning-Based Customer Churn Risk Prediction for Live Streaming e-Commerce},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 1: INCOFT},
year={2025},
pages={283-288},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013540000004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 1: INCOFT
TI - Machine Learning-Based Customer Churn Risk Prediction for Live Streaming e-Commerce
SN - 978-989-758-763-4
AU - Meng X.
AU - Li R.
AU - Song Q.
PY - 2025
SP - 283
EP - 288
DO - 10.5220/0013540000004664
PB - SciTePress