Research on the Application of Machine Learning in the Pricing of Cash Deposit Products

Xiao Jing

doi:10.71222/49bcs478

Authors

Xiao Jing Wealth Management, JP Morgan Chase, New Jersey, 07310, USA Author

DOI:

https://doi.org/10.71222/49bcs478

Keywords:

cash deposits, machine learning, intelligent pricing, financial technology, customer behavior modeling

Abstract

In the context of interest rate marketization and the vigorous development of financial technology innovation, the pricing of cash deposit products has a dilemma of real-time responding and personalization. Based on machine learning technology, this paper designs a price model path of data acquisition, attribute construction, algorithm screening and model practice. Through neural network, supply and demand curve optimization and other means, it quantitatively analyzes consumer behavior and product fit, empirically analyzes the effectiveness and operability of the model, and provides technical support for banks to optimize capital pricing efficiency and customer loyalty.

References

1. T. Alhalabi, V. Castro, and J. Wood, "Bank dividend payout policy and debt seniority: Evidence from US banks," Fin. Mark. Inst. Instrum., vol. 32, no. 5, pp. 285–340, 2023, doi: 10.1111/fmii.12183.

2. I. N. Widyanti, "The influence of liquid collateral types and credit processes through digital marketing on customer decisions to take cash collateral credit at Bank ABC," Jurnal Indonesia Sos. Teknol., vol. 5, no. 3, 2024, doi: 10.59141/jist.v5i3.981.

3. M. B. Pasha, R. N. Rao, S. Ismail, et al., "Tribo-informatics approach to predict wear and friction coefficient of Mg/Si₃N₄ composites using machine learning techniques," Tribol. Int., vol. 196, 2024, doi: 10.1016/j.triboint.2024.109696.

4. C. K. Ch’ng, "Hybrid machine learning approach for predicting e-wallet adoption among higher education students in Ma-laysia," J. Inf. Commun. Technol., vol. 23, no. 2, pp. 177–210, 2024, doi: 10.32890/jict2024.23.2.2.

5. C. Tang, Y. Qin, F. Wu, and Z. Tang, "Dynamic demand-aware power grid intelligent pricing algorithm based on deep re-inforcement learning," IEEE Access, vol. 12, pp. 75809–75817, 2024, doi: 10.1109/ACCESS.2024.3406338.