Muti-agent Generative Systems in E-commerce recommendations and pricing
Abstract
Multi-agent generative systems are transforming e-commerce by enhancing recommendation strategies and dynamic pricing mechanisms. These systems leverage multiple AI agents that collaborate using generative models, reinforcement learning, and market-driven strategies to optimize user engagement and revenue. By integrating customer behavior modeling, product preferences, and real-time market conditions, multi-agent frameworks facilitate personalized recommendations and adaptive pricing strategies. The synergy between generative AI and multi-agent collaboration enhances demand forecasting, reduces price volatility, and ensures competitive positioning. This paper explores the architecture, methodologies, and impact of multi-agent generative systems in e-commerce, highlighting their advantages over traditional approaches.
References
Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1798-1828.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33.
Chen, J., Zhao, X., & Wang, C. (2021). Personalized recommendation and pricing strategies in e-commerce: A review. Journal of Electronic Commerce Research, 22(3), 212-229.
Chen, L., & Li, W. (2017). The impact of dynamic pricing in e-commerce: The role of customer behavior and competitor actions. Journal of Retailing and Consumer Services, 34, 93-101.
Gao, T., & Zhu, J. (2020). Generative adversarial networks in recommender systems: A survey. ACM Computing Surveys, 53(4), 1-29.
He, X., & Chai, K. (2018). A hybrid approach to personalized recommendation and pricing. International Journal of Data Science and Analytics, 5(4), 249-262.
Li, X., & Ma, L. (2019). Reinforcement learning for dynamic pricing in e-commerce: A survey. Expert Systems with Applications, 128, 29-46.
Shih, Y., & Lu, Y. (2019). Multi-agent systems for personalized recommendation and dynamic pricing: A survey. International Journal of Artificial Intelligence, 10(2), 104-121.
Wang, Y., & Zhang, F. (2020). A deep learning-based multi-agent system for personalized pricing and recommendations in e-commerce. Journal of Artificial Intelligence Research, 67, 255-276.
Zhang, H., & Zhang, Z. (2020). Generative models for e-commerce personalization and pricing. Proceedings of the International Conference on E-commerce, 2020, 185-200.
