Detecting Financial Vulnerability in Urban Households Using Machine Learning: A Predictive Model for Early Risk Identification
Keywords:
Financial Vulnerability, Machine Learning, Predictive Modeling, XGBoost, SHAP, Urban Households, Hybrid ModelAbstract
Urban households in an emerging economy are facing financial vulnerability which is a growing socioeconomic concern and usually does not notice the traditional credit evaluation methods. This study proposes a machine learning-based model that will predict an early warning of financial vulnerability by integrating both behavioral and socioeconomic factors. A structured questionnaire was used to collect primary data comprising of 328 urban households with Indians. After data preprocess and feature engineering, three classification models were trained and compared including Logistic Regression, Random Forest, and XGBoost.The new hybrid ensemble model, based on XGBoost as a base learner and Logistic Regression as a meta-classifier, was created in order to be more predictive and interpretable. The hybrid method had the accuracy of 82 percent and ROC-AUC of 0.86. In order to be transparent of the model, SHAP (SHapley Additive explanations) analysis was conducted, and the most significant factors showed to be income, expense ratio, debt burden, and emergency savings, as well as financial confidence.At last, the model became a Flask-based web application and allowed to assess the vulnerabilities in real-time to be used practically. The research proposes a solution that is both scalable and data-driven to allow financial institutions and policymakers to actively determine the financially vulnerable households and intervene with such households before it becomes too late.
References
R. Gupta and S. Mehra, "An empirical analysis on household financial vulnerability in India," Journal of Economic Studies, vol. 45, no. 4, pp. 210–229, 2023.
D. Sharma, "Decoding financial behaviour: Urbanised households in India using AIDIS 77th round," Indian Journal of Urban Economics, vol. 12, no. 2, pp. 101–120, 2024.
Oesterreichische Nationalbank, "Making sense of financial vulnerability," OeNB Financial Stability Report, vol. 44, pp. 56–74, 2022.
Consumer Financial Protection Bureau, "Emergency savings and financial security," Washington, D.C.: CFPB Publications, 2022.
R. Das and P. Nair, "Digital financial literacy and household resilience," Journal of Digital Economics, vol. 8, no. 1, pp. 88–102, 2024.
Vanguard, "Emergency savings and financial well-being," Vanguard Research Institute Report, 2022.
UNICEF, "Food insecurity through a machine learning lens," United Nations Publications, 2021.
S. Balaji, R. Gupta, and N. Mehra, "Predicting household financial distress using machine learning: A cross- sectional study of urban India," Journal of Financial Analytics, vol. 14, no. 3, pp. 120–133, 2022.
[Nvissi Project Team, "Novissi case study — Targeting with satellite and phone data," World Bank Working Paper Series, 2021.
A. Kumar and R. Singh, "Poverty mapping in India using machine learning and deep learning," Journal of Development Data Science, vol. 5, no. 2, pp. 155–172, 2022.
F. Yuliani, D. Raharjo, and A. Prasetyo, "Predicting household resilience before and during pandemic," Asian Economic Review, vol. 47, no. 1, pp. 78–95, 2022.
M. Patel, "Understanding household vulnerability in urban India," Indian Economic Journal, vol. 68, no. 2, pp. 233–250, 2020.
J. Wilson and L. Carter, "Machine learning approaches to consumer financial health," Journal of Financial Data Science, vol. 3, no. 1, pp. 45–60, 2021.
S. Kaur and P. Reddy, "Coping with income shocks: A household perspective," Economic & Social Studies, vol. 11, no. 4, pp. 90–108, 2019.
T. Hamilton and J. Brooks, "Assessing household financial vulnerability in the U.S.," American Economic Review, vol. 111, no. 5, pp. 305–329, 2021.
M. Fernandez and R. Lopez, "Household debt and financial fragility in emerging economies," Latin American Journal of Economics, vol. 57, no. 3, pp. 200–223, 2020.
J. Park and D. Lee, "Reproducible XGBoost + SHAP pipelines for early warning," Computational Finance Journal, vol. 9, no. 2, pp. 145–163, 2021.
Cambridge Centre for Alternative Finance, "State of SupTech Report 2023," University of Cambridge Publications, 2023. [19] S. Nanda and P. Roy, "Financial well-being in India: A survey-based analysis," Journal of Indian Financial Studies, vol. 16, no. 2, pp. 180–197, 2022.
T. Bhattacharya, "Household vulnerability and coping in post-pandemic India," Journal of Urban Economics and Policy, vol. 10, no. 3, pp. 155–172, 2023.
Consumer Financial Protection Bureau, "Measuring financial well-being: A guide to using the CFPB Financial Well-Being Scale," U.S. Government Publishing Office, 2022.
A. Lusardi and O. S. Mitchell, "The economic importance of financial literacy: Theory and evidence," Journal of Economic Literature, vol. 52, no. 1, pp. 5–44, 2014.
M. T. Ribeiro, S. Singh, and C. Guestrin, "“Why should I trust you?”: Explaining the predictions of any classifier," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2016, pp. 1135–1144.
S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Adv. Neural Inf. Process. Syst., 2017, vol. 30.
T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2016, pp. 785–794.
M. Kuhn and K. Johnson, Feature Engineering and Selection: A Practical Approach for Predictive Models. Chapman & Hall/CRC, 2019.
OECD, "Financial literacy and inclusion: Results of OECD/INFE survey," OECD Publishing, 2021. [Online]. Available: https://www.oecd.org/financial/education/
