Abstract
A basic concept of loan is reconsidered all over the world by the new BIS regulations. However, many people in Latin America still have a vague way of thinking about loans. It is due to the global recession. As a result, companies have not been able to recover their manufacturing costs. However, a large potential market has been formed in Latin America. Therefore, the challenge for companies is how to formulate product strategies that can meet the needs of the market. Therefore, in this study, we create a classification model of whether customers will default or not. In addition, we explore the characteristics of the default customers. Propose a sales strategy for the product based on these characteristics. This would help companies to improve their financing problems and secure profits. In this study, we compare the accuracy of Logistic Regression, Random Forest and XGBoost. Since the data handled in this study were unbalanced data, data expansion by Synthetic Minority Over-sampling Technique (SMOTE) was effective. Finally, we analyze analyzes what variables contribute to the model by using SHapley Additive exPlanations (SHAP). From this analysis result, we will explore the characteristics of what kind of person is the loan unpaid customers. The variables with the highest contribution were the type of vehicle purchased, the area where the customer lives, and credit information. We propose sales strategy by focusing on the variables that are significant to the model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Yamashita, T., Kawaguchi, N., Tsuruga, T.: A Study and Comparison of Evaluation Methods for Credit Risk Models. Financial Research and Training Center, Financial Services Agency, Discussion Paper (2003)
Fukumitsu, H.: On strategic default. Seijo Univ. Keizai Kenkyu 193, 179–234 (2011)
Amano, T., Shintaku, J.: ASEAN strategy of Honda’s motorcycle business: introduction of low-cost model and innovation of product strategy. Akamon Manage. Rev. 9(11), 783–806 (2010)
Matsunaga, T.: Interpretability of a Data-Driven Credit Scoring Model for Developing Countries: An Analysis of Customer Data from a Vietnamese Shipping Commercial Bank (2021)
Miyoshi, Y.: An empirical study of adverse selection in consumer finance markets. Kagawa Univ. Econ. Rev. 88(4), 529–553 (2016)
Guiso, L., Sapienza, P., Zingales, L.: The determinants of attitudes toward strategic default on mortgages. J. Financ. 68(4), 1473–1515 (2013)
Sawaki, T., Tanaka, T., Kasahara, R.: Building a Credit Scoring Model for Small and Medium Enterprises Using Machine Learning, Artificial Intelligence Research Group Materials (2017)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Hall, M.A.: Correlation-based feature selection for machine learning (1999)
Yoshida, H., Tajima, Y., Imai, Y.: A test of the usefulness of SHAP values in the interpretation of decision tree models. In: Proceedings of the 34th National Convention of the Japanese Society for Artificial Intelligence. Japanese Society for Artificial Intelligence (2020). 3E5GS204-3E5GS204
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4768–4777 (2017)
Ogi, K., Toshiro, M., Hibiki, N.: The relationship between the robustness of the business history function and the amount of personal assets of the manager in the credit scoring model for small firms. Japan. J. Oper. Res. 59, 134–159 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fujinuma, R., Asahi, Y. (2022). Default Factors in Motorcycle Sales in Developing Countries. In: Yamamoto, S., Mori, H. (eds) Human Interface and the Management of Information: Visual and Information Design. HCII 2022. Lecture Notes in Computer Science, vol 13305. Springer, Cham. https://doi.org/10.1007/978-3-031-06424-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-06424-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06423-4
Online ISBN: 978-3-031-06424-1
eBook Packages: Computer ScienceComputer Science (R0)