An interpretable predictive model for bank customers’ income using the eXtreme Gradient Boosting algorithm and the SHAP method: a case study of an Anonymous Chilean Bank

References

• Alsahaf A, Petkov N, Shenoy V, Azzopardi G. 2022. A framework for feature selection through boosting. Expert Syst Appl. 187:115895.
   Web of Science ®Google Scholar
• Alsaleh N, Farooq B. 2021. Interpretable data-driven demand modelling for on-demand transit services. Transp Res Part A Policy Pract. 154:1–22.
   Web of Science ®Google Scholar
• Ambrey CL, Fleming CM. 2014. The causal effect of income on life satisfaction and the implications for valuing non-market goods. Econ Lett. 123(2):131–134.
   Web of Science ®Google Scholar
• Bergstra J, Yamins D, Cox D. 2013. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In: International Conference on Machine Learning. PMLR. p.115–123.
   Google Scholar
• Breiman L. 2001. Random forests. Mach Learn. 45:5–32.
   Web of Science ®Google Scholar
• Burlacu M. 2016. The population’income, expenses and savings as descriptive aspects of the standard of living. Ovidius Univ Ann Series Econ Sci. 16(2):175–180.
   Google Scholar
• Bussolo M, Davalos ME, Peragine V, Sundaram R. 2018. Toward a new social contract: taking on distributional tensions in Europe and Central Asia. World Bank Publications.
   Google Scholar
• Cai Q, Abdel-Aty M, Zheng O, Wu Y. 2022. Applying machine learning and google street view to explore effects of drivers’ visual environment on traffic safety. Transp Res Part C: Emerg Technol. 135:103541.
   Web of Science ®Google Scholar
• Chen T, Guestrin C. 2016. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. p. 785–794.
   Google Scholar
• Chia G, Miller PW. 2008. Tertiary performance, field of study and graduate starting salaries. Aust Econ Rev. 41(1):15–31.
   Web of Science ®Google Scholar
• Fafoutellis P, Mantouka EG, Vlahogianni EI. 2022. Acceptance of a pay-how-you-drive pricing scheme for city traffic: the case of athens. Transp Res Part A Policy Pract. 156:270–284.
   Web of Science ®Google Scholar
• Fan J, Wang X, Wu L, Zhou H, Zhang F, Yu X, Lu X, Xiang Y. 2018. Comparison of support vector machine and extreme gradient boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: a case study in china. Energy Convers Manage. 164:102–111.
   Web of Science ®Google Scholar
• Fuders F. 2023. Economic resilience in the face of external shocks. In: How to Fulfil the UN sustainability goals: rethinking the role and concept of money in the light of sustainability. Cham: Springer. p. 327–344
   Google Scholar
• Futagami K, Fukazawa Y, Kapoor N, Kito T. 2021. Pairwise acquisition prediction with shap value interpretation. J Finance Data Sci. 7:22–44.
   Google Scholar
• García-Alonso CR, Torres-Jiménez M, Hervás-Martínez C. 2010. Income prediction in the agrarian sector using product unit neural networks. Eur J Oper Res. 204(2):355–365.
   Web of Science ®Google Scholar
• Goldberg LR, Mouti S. 2022. Sustainable investing and the cross-section of returns and maximum drawdown. J Finance Data Sci. 8:353–387.
   Google Scholar
• Gunning D, Stefik M, Choi J, Miller T, Stumpf S, Yang G-Z. 2019. Xai-explainable artificial intelligence. Sci Robot. 4(37):eaay7120.
   PubMed Web of Science ®Google Scholar
• Hughes G. 1968. On the mean accuracy of statistical pattern recognizers. IEEE Trans Inf Theory. 14(1):55–63.
   Web of Science ®Google Scholar
• Jaquart P, Dann D, Weinhardt C. 2021. Short-term bitcoin market prediction via machine learning. Finance Data Sci. 7:45–66.
   Google Scholar
• Keany E. 2020. Borutashap: A wrapper feature selection method which combines the Boruta feature selection algorithm with Shapley values (Version 1.1). Zenodo.
   Google Scholar
• Kibekbaev A, Duman E. 2016. Benchmarking regression algorithms for income prediction modeling. Inf Syst. 61:40–52.
   Web of Science ®Google Scholar
• Kursa MB, Rudnicki WR. 2010. Feature selection with the Boruta package. J Stat Soft. 36(11):1–13.
   Web of Science ®Google Scholar
• Ładyżyński P, Żbikowski K, Gawrysiak P. 2019. Direct marketing campaigns in retail banking with the use of deep learning and random forests. Expert Syst Appl. 134:28–35.
   Web of Science ®Google Scholar
• Lang X, Wu D, Mao W. 2022. Comparison of supervised machine learning methods to predict ship propulsion power at sea. Ocean Eng. 245:110387.
   Web of Science ®Google Scholar
• Lazar A. 2004. Income prediction via support vector machine. In: ICMLA. p. 143–149.
   Google Scholar
• Lin K, Gao Y. 2022. Model interpretability of financial fraud detection by group shap. Expert Syst Appl. 210:118354.
   Web of Science ®Google Scholar
• Lundberg SM, Lee, SI. 2017. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 30.
   Google Scholar
• Lundberg SM, Erion GG, Lee SI. 2018. Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888.
   Google Scholar
• Matkowski M. 2021. Prediction of individual income: A machine learning approach. Bryant Online Repository. Rhode Island: Bryant University.
   Google Scholar
• Miller T. 2017. Explanation in artificial intelligence: insights from the social sciences. Artif Intell. 267:1–38.
   Web of Science ®Google Scholar
• Mokhtari KE, Higdon BP, Başar A. 2019. Interpreting financial time series with shap values. In: Proceedings of the 29th Annual International Conference on Computer Science and Software Engineering. p. 166–172.
   Google Scholar
• Molnar C. 2020. Interpretable machine learning. Lulu. com.
   Google Scholar
• Padarian J, McBratney AB, Minasny B. 2020. Game theory interpretation of digital soil mapping convolutional neural networks. Soil. 6(2):389–397.
   Web of Science ®Google Scholar
• Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. 2011. Scikit-learn: Machine learning in python. J Mach Learn Res. 12(Oct):2825–2830.
   Google Scholar
• Pinelis M, Ruppert D. 2022. Machine learning portfolio allocation. J Finance Data Sci. 8:35–54.
   Google Scholar
• Ross G, Das S, Sciro D, Raza H. 2021. Capitalvx: a machine learning model for startup selection and exit prediction. J Finance Data Sci. 7:94–114.
   Google Scholar
• Salas P, De la Fuente R, Astroza S, Carrasco JA. 2022. A systematic comparative evaluation of machine learning classifiers and discrete choice models for travel mode choice in the presence of response heterogeneity. Expert Syst Appl. 193:116253.
   Web of Science ®Google Scholar
• Shapley LS. 1953. A value for n-person games. Contrib Theory Games. 2(28):307–317.
   Google Scholar
• Shin S, Austin PC, Ross HJ, Abdel-Qadir H, Freitas C, Tomlinson G, Chicco D, Mahendiran M, Lawler PR, Billia F, Gramolini A, Epelman S, Wang B, Lee DS. 2021. Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality. ESC Heart Failure 8(1):106–115.
   PubMed Web of Science ®Google Scholar
• Silva CAO, Gonzalez-Otero R, Bessani M, Mendoza LO, de Castro CL. 2022a. Interpretable risk models for sleep apnea and coronary diseases from structured and non-structured data. Expert Syst Appl. 200:116955.
   Web of Science ®Google Scholar
• Silva I, Ferreira C, Costa L, Sóter M, Carvalho L, Albuquerque DCJ, Sales M, Candido A, Reis F, Veloso A, et al. 2022b. Polycystic ovary syndrome: clinical and laboratory variables related to new phenotypes using machine-learning models. J Endocrinol Invest. 45:497–505.
   PubMed Web of Science ®Google Scholar
• Singh GD, Vig H, Kumar A. 2021. A data visualization approach for predicting the income class of the population. In: 2021 5th International Conference on Electronics, Communication and Aerospace Technology (ICECA). IEEE. p. 1042–1047.
   Google Scholar
• Smart JC. 1988. College influences on graduates’ income levels. Res High Educ. 29:41–59.
   Web of Science ®Google Scholar
• Swan N. 2006. Problems in dynamic modeling of individual incomes. In: Swedish Conference on Microsimulation, Stockholm. Vol. 20.
   Google Scholar
• Thomas SL. 2000. Deferred costs and economic returns to college major, quality, and performance. Res High Educ. 41:281–313.
   Web of Science ®Google Scholar
• Trunk GV. 1979. A problem of dimensionality: a simple example. IEEE Trans Pattern Anal Mach Intell. PAMI-1(3):306–307.
   PubMed Web of Science ®Google Scholar
• Vythoulkas PC, Koutsopoulos HN. 2003. Modeling discrete choice behavior using concepts from fuzzy set theory, approximate reasoning and neural networks. Transp Res Part C Emerg Technol. 11(1):51–73.
   Web of Science ®Google Scholar
• Wang H, Liu C, Deng L. 2018. Enhanced prediction of hot spots at protein-protein interfaces using extreme gradient boosting. Sci Rep. 8(1):1–13.
   PubMed Web of Science ®Google Scholar
• Wu J, Chen X-Y, Zhang H, Xiong L.D, Lei H, Deng S-H. 2019. Hyperparameter optimization for machine learning models based on Bayesian optimization. J Electron Sci Technol. 17(1):26–40.
   Google Scholar
• Yu D, Liu Z, Su C, Han Y, Duan, X, Zhang, R, Liu, X, Yang, Y, Xu, S. 2020a. Copy number variation in plasma as a tool for lung cancer prediction using extreme gradient boosting (xgboost) classifier. Thorac Cancer. 11(1):95–102.
   PubMed Web of Science ®Google Scholar
• Yu GB, Lee D-J, Sirgy MJ, Bosnjak M. 2020b. Household income, satisfaction with standard of living, and subjective well-being. the moderating role of happiness materialism. J. Happiness Stud. 21:2851–2872.
   Web of Science ®Google Scholar