Prediction for the Customer Behavior in the Financial Institution Based on the Machine Learning Algorithms

Hongyu Deng

doi:10.54691/bcpbm.v28i.2239

Authors

Hongyu Deng

DOI:

https://doi.org/10.54691/bcpbm.v28i.2239

Keywords:

Customer behavior, neural network, feature importance, random forest.

Abstract

Investigation for the customer behavior is an emerging field that many studies fouces on in the past. In the field of the bank, predicting whether the customr will leave or not is an important question. This study mainly tries to figure out what is the most influencing factor of a customer when they choose to exit tone financial institution. It is important that the company get the rational prediction, which could help them to make the right decosison to maintain and retain the customers. We use the random forst and Neuralnetwork algorithm to do the process. The factor age is the most influencing factor which world affect the exiting decision. This paper firstly predicted that the factor age is the most influencing factor, since the age is a factor which could make the customer change their decision based on their experiences and savings. Generally speaking, the results fit the prediction in this study. The results of this work is that the factor age is the most influencing one, and the factor gender matters the least. Other factors such as CreditScore and Salary are also play an important role when the customers make the exiting decision. Besides, there is also an interesting finding. The German customers seem to be more possible to exit one financial institution.

Downloads

Download data is not yet available.

References

Ezenkwu, Chinedu Pascal, Simeon Ozuomba, and Constance Kalu. Application of K-Means algorithm for efficient customer segmentation: a strategy for targeted customer services [J]. (2015).

Qiu, Yuhang, et al. Clustering Analysis for Silent Telecom Customers Based on K-means++ [C]. 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). Vol. 1. IEEE, 2020. DOI: https://doi.org/10.1109/ITNEC48623.2020.9084976

Syakur, M. A., et al. Integration k-means clustering method and elbow method for identification of the best customer profile cluster [C]. IOP conference series: materials science and engineering. Vol. 336. No. 1. IOP Publishing, 2018. DOI: https://doi.org/10.1088/1757-899X/336/1/012017

Kansal, Tushar, et al. Customer segmentation using K-means clustering [C]. 2018 international conference on computational techniques, electronics and mechanical systems (CTEMS). IEEE, 2018. DOI: https://doi.org/10.1109/CTEMS.2018.8769171

Zare, Hamed, and Sima Emadi. Determination of Customer Satisfaction using Improved K-means algorithm [J]. Soft Computing 24.22 (2020): 16947-16965. DOI: https://doi.org/10.1007/s00500-020-04988-4

Oshiro, Thais Mayumi, Pedro Santoro Perez, and José Augusto Baranauskas. How many trees in a random forest? [C]. International workshop on machine learning and data mining in pattern recognition. Springer, Berlin, Heidelberg, 2012. DOI: https://doi.org/10.1007/978-3-642-31537-4_13

Probst, Philipp, Marvin N. Wright, and Anne‐Laure Boulesteix. Hyperparameters and tuning strategies for random forest [J]. Wiley Interdisciplinary Reviews: data mining and knowledge discovery 9.3 (2019): e1301. DOI: https://doi.org/10.1002/widm.1301

Probst, Philipp, and Anne-Laure Boulesteix. To tune or not to tune the number of trees in random forest [J]. J. Mach. Learn. Res. 18.1 (2017): 6673-6690.

Abiodun, Oludare Isaac, et al. State-of-the-art in artificial neural network applications: A survey [J]. Heliyon 4.11 (2018): e00938. DOI: https://doi.org/10.1016/j.heliyon.2018.e00938

Wang, Sun-Chong. Artificial neural network [J]. Interdisciplinary computing in java programming. Springer, Boston, MA, 2003. 81-100. DOI: https://doi.org/10.1007/978-1-4615-0377-4_5

Hecht-Nielsen, Robert. Theory of the backpropagation neural network [J]. Neural networks for perception. Academic Press, 1992. 65-93. DOI: https://doi.org/10.1016/B978-0-12-741252-8.50010-8

Kaggle, bank customer churn prediction, https://www.kaggle.com/datasets/shantanudhakadd/bank-customer-churn-prediction, 2022