Application and Optimization of Various Machine Learning Models in Social E-Commerce Marketing Strategies


  • Zhen Li



Marketing Strategies, Artificial Intelligence, Deep Learning, Personalized Recommendation, User Behavior Prediction.


In the context of rapid development in social e-commerce, the optimization of marketing strategies urgently requires new technological approaches. This study investigates the application of four artificial intelligence algorithms—supervised learning, deep learning, unsupervised learning, and reinforcement learning—in Douyin live shopping and Kuaishou platform shopping, proposing a series of innovative marketing strategies. Based on an analysis of 920,000 user behavior records, we evaluate the effectiveness of each algorithm in user behavior prediction, personalized recommendation, advertisement placement optimization, and customer segmentation. The results indicate that the deep learning model achieved a prediction accuracy of 94.8%, enhancing user satisfaction by 19.7%. The supervised learning model achieved a classification accuracy of 89.3%. The reinforcement learning model increased advertisement click-through rates by 24.6%. The unsupervised learning model excelled in customer segmentation. By utilizing hybrid models and improved algorithms, marketing effectiveness was further enhanced, providing new directions and strategies for marketing practices in the social e-commerce sector.


Download data is not yet available.


Michalski, R. S., Carbonell, J. G., & Mitchell, T. M. (Eds.). (2013). Machine learning: An artificial intelligence approach. Springer Science & Business Media.

Kim, S., Yu, Z., Kil, R. M., & Lee, M. (2015). Deep learning of support vector machines with class probability output networks. Neural Networks, 64, 19-28.

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.

MacQueen, J. (1967, June). Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability (Vol. 1, No. 14, pp. 281-297).

Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.

Zhu, Z., & Van Roy, B. (2023, September). Deep exploration for recommendation systems. In Proceedings of the 17th ACM Conference on Recommender Systems (pp. 963-970).

Lou, K., Yang, Y., Wang, E., Liu, Z., Baker, T., & Bashir, A. K. (2020). Reinforcement learning based advertising strategy using crowdsensing vehicular data. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4635-4647.

Hemadharshini, S. M., Kanchana Devi, R., Rajakumari, S., & Adline Freeda, R. (2023, June). E-commerce Customer Segmentation by Unsupervised Learning. In International Conference on Soft Computing and Signal Processing (pp. 285-296). Singapore: Springer Nature Singapore.




How to Cite

“Application and Optimization of Various Machine Learning Models in Social E-Commerce Marketing Strategies” (2024) Transactions on Computer Science and Intelligent Systems Research, 4, pp. 11–21. doi:10.62051/bsm4y952.

Similar Articles

1-10 of 47

You may also start an advanced similarity search for this article.