Building an AI Product Selection Optimization Model for Food Categories in Live-Streaming E-Commerce: A Multi-Dimensional Interactive Real-Time Selection Optimization Model (MDISOM)

DOI

10.2991/978-94-6463-916-2_52How to use a DOI?

Keywords

Live-streaming e-commerce; Food selection; Artificial intelligence; Multi-dimensional model; Real-time optimization; Human-machine collaboration

Abstract

With the explosive growth of live-streaming e-commerce, traditional product selection methods struggle to meet the demands of the food category due to its characteristics such as short shelf life, strong seasonality, and low stand-ardization. This study proposes the Multi-Dimensional Interactive Real-Time Product Selection Optimization Model (MDISOM), which integrates five dimen-sions: product features, real-time interaction data, host characteristics, spatiotem-poral factors, and supply chain status. It achieves dynamic product selection op-timization through multimodal deep learning and reinforcement learning. Experi-ments demonstrate that MDISOM significantly outperforms baseline models in accuracy (84.7%), F1 score (0.834), and AUC (0.896). Practical applications achieved a 22.7% increase in sales revenue, an 18.9% boost in conversion rate, and a 15.3% improvement in inventory turnover efficiency. This study also vali-dates the effectiveness of a human-machine collaborative semi-automated product selection system, providing a theoretical framework and technical solution for food product selection in live-streaming e-commerce.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xiaofang Zhang
AU  - Kunyu Lu
AU  - Huihua Zheng
AU  - Jiachun Lin
AU  - Heli Zhang
PY  - 2025
DA  - 2025/12/22
TI  - Building an AI Product Selection Optimization Model for Food Categories in Live-Streaming E-Commerce: A Multi-Dimensional Interactive Real-Time Selection Optimization Model (MDISOM)
BT  - Proceedings of the 2025 4th International Conference on Public Service, Economic Management and Sustainable Development (PESD 2025)
PB  - Atlantis Press
SP  - 485
EP  - 493
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-916-2_52
DO  - 10.2991/978-94-6463-916-2_52
ID  - Zhang2025
ER  -