Research on Intelligent Platform Economy Pricing Model Based on Network Traffic and User Profiling Data

Yiting Shi

doi:10.62051/ijcsit.v4n3.01

Authors

Yiting Shi

DOI:

https://doi.org/10.62051/ijcsit.v4n3.01

Keywords:

Dynamic pricing, Platform economy, Deep learning, Convolutional neural networks, Deep reinforcement learning, Personalized pricing treatmentaries E-commerce optimization

Abstract

The platform economy evolved rapidly due to technological breakthroughs, hence new challenges emerged in terms of pricing strategies affected from different user behaviors and market demand dynamics. Traditional pricing methods are not up to this type of challenge, and it requires a model able to be more agile — in real time. The study presents “DeepPrice,” a dynamic pricing model using deep learning namely Convolutional Neural Networks (CNN) and Deep Reinforcement Learning (DRL) to achieve the optimal platform pricing strategies in response to user behavior and market signals. The research has an experimental design for the development and testing of the DeepPrice model. The model is pre-trained by the transaction data of an important e-commerce platform for this task. CNNs learn user profiles and product properties via the encoding layer, while DRL models implement the strategy of adjusting price according to behavior actions in tensor form. Metrics such as platform revenue, user conversion rates, and customer satisfaction are used to validate the model back to the model performance. Our solution helped DeepPrice to generate incremental 20% platform revenue on average and better adjust to the market challenges. It performed better than standard pricing solutions, especially in times of high demand, and effectively personalized price-pointing for top-value customers to drive higher conversions and improve customer satisfaction. This study points to the promise of using deep learning to improve dynamic pricing in platform economies. Flexible & Scalable Solution for any IndustryDeepPrice Nevertheless, challenges regarding the computational cost of implementing personalized pricing strategies and ethical debates surrounding such strategies remain to be studied in more detail. In platform economy, the reinforcement learner has a significant potential to provide a reliable real-time pricing solution with CNN in DeepPrice to improve both profit and customer satidfaction.

Downloads

Download data is not yet available.

References

[1] Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., ... & Zheng, X. (2016). TensorFlow: A system for large-scale machine learning. In 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16) (pp. 265-283).

[2] Grewal, D., Roggeveen, A. L., & Nordfält, J. (2017). The future of retailing. Journal of Retailing, 93(1), 1-6. https://doi.org/10.1016/j.jretai.2016.12.008

[3] Guo, L. (2020). Cross-border e-commerce platform for commodity automatic pricing model based on deep learning. Electronic Commerce Research, 20(4), 615-631. https://doi.org/10.1007/s10660-020-09449-6

[4] Haarnoja, T., Zhou, A., Abbeel, P., & Levine, S. (2018). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290.

[5] Huang, J., Huang, L., Liu, M. L., Li, H., Tan, Q., Ma, X., Cui, J., & Huang, D. S. (2022). Deep reinforcement learning-based trajectory pricing on ride-hailing platforms. ACM Transactions on Intelligent Systems and Technology, 13(3), 20-34. https://doi.org/10.1145/3474841

[6] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).

[7] Lambrecht, A., & Tucker, C. (2013). When does retargeting work? Information specificity in online advertising. Journal of Marketing Research, 50(5), 561-576. https://doi.org/10.1509/jmr.11.0503

[8] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539

[9] Liu, J., Zhang, Y., Wang, X., Deng, Y., & Wu, X. (2019). Dynamic pricing on e-commerce platform with deep reinforcement learning: A field experiment. arXiv preprint arXiv:1912.02091.

[10] Risselada, H., Verhoef, P. C., & Bijmolt, T. H. (2014). Dynamic effects of social influence and direct marketing on the adoption of high-technology products. Journal of Marketing, 78(2), 52-68. https://doi.org/10.1509/jm.11.0416

[11] Shi, B., Shi, R., & Li, B. (2020). Multi-agent deep reinforcement learning-based pricing strategy for competing cloud platforms in the evolutionary market. In Proceedings of the International Conference on Web Services (ICWS) (pp. 150-159). https://doi.org/10.1109/ICWS49710.2020.00028

[12] Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.

[13] Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.

[14] Zhang, Y., Liu, J., & Chen, W. (2020). Pricing under user behavior dynamics: A reinforcement learning approach. IEEE Transactions on Neural Networks and Learning Systems, 31(6), 1820-1830. https://doi.org/10.1109/TNNLS.2019.2956841