Author(s)

YuanJia Guo

Affiliation(s)

Management of National Economics, Renmin University of China, Beijing 100872, China.

Corresponding Author

YuanJia Guo

ABSTRACT

This study examines the differences in characteristics between customers who purchase deposit products and those who do not, using relevant information from a bank's customer dataset. The key features analyzed include customer ID, age, occupation, marital status, credit card default history, mortgage status, contact method, last contact month and duration, the three-month interbank lending rate, previous marketing campaign results, the number of contacts before the current campaign, the number of days since the last contact, employment variation rate, consumer price index, consumer confidence index, number of employees, and whether the customer purchased a deposit product. Python is employed for descriptive analysis and classification analysis, and decision tree, logistic regression, and random forest models are used to predict whether a customer will purchase a deposit product. The analysis results reveal key factors influencing customer decisions, providing insights for banks to conduct targeted marketing within limited time frames, increase the likelihood of customer purchases, and ultimately improve overall deposit performance.

KEYWORDS

Bank customers; Deposit products; Descriptive analysis; Classification analysis; Decision tree, Logistic regression; Random forest; Model prediction

CITE THIS PAPER

YuanJia Guo. Bank customer deposit product purchase analysis and prediction. Journal of Trends in Financial and Economics. 2025, 2(2): 13-22. DOI: https://doi.org/10.61784/jtfe3038.

REFERENCES

[1] Hao Liancai, Zou Peng, Li Yijun. The impact of sales promotion based on observational learning on customer purchase intention. Journal of System Management, 2012, 21(6): 795-801.

[2] Mahesh B. Machine learning algorithms-a review. International Journal of Science and Research (IJSR), 2020, 9(1): 381-386.

[3] Singh A, Thakur N, Sharma A. A review of supervised machine learning algorithms//2016 3rd international conference on computing for sustainable global development (INDIACom). Ieee, 2016: 1310-1315.

[4] Yang Xuebing, Zhang Jun. Decision tree algorithm and its core technology. Computer Technology and Development, 2007, 17(1): 43-45.

[5] Qiu Hong, Yu Dexin, Wang Xiaorong, et al. Analysis and evaluation of interaction effects in the logistic regression model. Chinese Journal of Epidemiology, 2008, 29(9): 934-937.

[6] Lü Hongyan, Feng Qian. A review of research on the random forest algorithm. Journal of Hebei Academy of Sciences, 2019, 36(3): 37-41.

[7] Leo M, Sharma S, Maddulety K. Machine learning in banking risk management: A literature review. Risks, 2019, 7(1): 29.

[8] Lu Haiyan. Research on customer satisfaction in commercial banks. China Market, 2008 (44): 31-33.

[9] Petropoulos A, Siakoulis V, Stavroulakis E, et al. Predicting bank insolvencies using machine learning techniques. International Journal of Forecasting, 2020, 36(3): 1092-1113.

[10] Hu L, Chen J, Vaughan J, et al. Supervised machine learning techniques: An overview with applications to banking. International Statistical Review, 2021, 89(3): 573-604.

[11] Munkhdalai L, Munkhdalai T, Namsrai O E, et al. An empirical comparison of machine-learning methods on bank client credit assessments. Sustainability, 2019, 11(3): 699.

[12] Carbo-Valverde S, Cuadros-Solas P, Rodríguez-Fernández F. A machine learning approach to the digitalization of bank customers: Evidence from random and causal forests. Plos one, 2020, 15(10): e0240362.

[13] Donepudi P K. Machine learning and artificial intelligence in banking. Engineering International, 2017, 5(2): 83-86.

[14] Guerra P, Castelli M. Machine learning applied to banking supervision a literature review. Risks, 2021, 9(7): 136.