Application of Precise Loan Qualification Identification Based on K-Means and Decision Tree Model from the Perspective of Consumer Behavior in Universities
- 1 School of Mathematical Sciences, Jiangsu University, Zhenjiang, China
- 2 School of Mathematical Sciences, Jiangsu University, Zhenjiang, China
- 3 School of Mathematical Sciences, Jiangsu University, Zhenjiang, China
Abstract
From the perspective of student consumption behavior, a data-driven framework for screening student loan eligibility was developed using K-means clustering analysis and decision tree models. A questionnaire survey was conducted on 829 students at colleges and universities to collect comprehensive data covering various dimensions such as economic background and consumption patterns. The K-means algorithm successfully predicted and identified the loan eligibility of the samples, with its predictive performance demonstrated by combining it with the decision tree model. Additionally, through in-depth discussions with credit departments, its practical value and reliability were confirmed. This study has enhanced the data-driven intelligent decision mechanism and provided strong support for precise loan disbursement in student loans, paving the way for the application of financial technology in credit areas.
- Cao, G. G., Li, M. X., Chen, Y. et al. (2021). Improved Support Vector Machine Classification Method and Its Application in Primary Liver Cancer Screening. Journal of Applied Sciences, 39 , 481-494. (In Chinese)
- Fang, K. N., Wu, J. B., Zhu, J. P. et al. (2011). A Review of Random Forest Methodology Research. Statistics & Information Forum, 26 , 32-38. (In Chinese)
- Kong, Y. H., & Jing, M. L. (2012). Research on Classification Method Based on Confusion Matrix and Ensemble Learning. Computer Engineering & Science, 34 , 111-117. (In Chinese)
- Li, J., & Bai, J. (2014). Measurement of Regional Financial Agglomeration Level in China. Seeking Truth, 41 , 52-58. (In Chinese)
- Liang, J., Chen, J. H., Zhang, X. Q. et al. (2019). Anomaly Detection Based on One-Hot Encoding and Convolutional Neural Network. Journal of Tsinghua University (Science and Technology), 59 , 523-529. (In Chinese)
- Lin, H. M., & Zhang, W. L. (2005). Similarities and Differences between Principal Component Analysis and Factor Analysis and SPSS Software—Also Discussing with Comrades Liu Yumei, Lu Wendai, etc. Statistical Research, No . 3 , 65-69. (In Chinese)
- Liu, L. X., Zhang, T., & Yang, M. (2018). Calculation and Correction of Cronbach’s α Coefficient Using Multilevel Models. Chinese Journal of Health Statistics, 35 , 838-842. (In Chinese)
- Long, W. J., Zhang, X. F., & Zhang, L. (2020). Business Process Clustering Method Based on K-Means and Elbow Rule. Journal of Jianghan University (Natural Science Edition), 48 , 81-90. (In Chinese)
- Luan, L. H., & Ji, G. L. (2004). Research on Decision Tree Classification Technology. Computer Engineering, No . 9 , 94-96, 105. (In Chinese)
- Meng, Z. J. (2017). Research on the Spatiotemporal Behavior Characteristics of Linear Sports Activities in Beijing Central City Streets. Ph.D. Thesis, Harbin Institute of Technology. (In Chinese)
- Niu, Z. X., & Cai, K. Y. (2007). Design of a Multi-Level Distributed Intelligent Decision Support System Based on Regression Algorithm. Computer Engineering and Design, No. 16 , 4004-4006. (In Chinese)
- Sun, J. G., Liu, J., & Zhao, L. Y. (2008). Clustering Algorithm Research. Journal of Software, No . 1 , 48-61. (In Chinese)
- Wang, Q., Wang, C., Feng, Z. Y. et al. (2012). Survey of K-Means Clustering Algorithm Research. Electronic Design Engineering, 20 , 21-24. (In Chinese)