Empowering Members: Launching Risk-Aware Overdraft Systems to Enhance Financial Resilience
DOI:
https://doi.org/10.15662/IJEETR.2023.0506007Keywords:
Banking Systems, Risk Modeling, Member Eligibility, Product Strategy, Backend Engineering, Financial ResilienceAbstract
The growing rate of financial instability among the banking members has highlighted the need to have intelligent overdraft systems that reduce the risks and maintain a trade of between accessibility and risk reduction. The study presents a risk-sensitive overdraft system which can enable members by using predictive analytics, adaptive eligibility modeling, and dynamic product strategy combination. The system allows making decisions regarding overdraft eligibility and transaction risk scoring in near-real-time. Its methodology uses risk modeling through machine learning, with historical data of transactions and behavioral factors to determine the financial strength of the member. The Kafka-based event stream will work as the coordinator of the communication between the risk evaluation modules and the backend services, whereas the analytical foundation is BigQuery that will be used to perform massive data aggregation and computation of features. Whimsical and Jira were used as systems architecture and sprint-based agile implementation tools to develop the prototype, respectively.As the analysis of the results shows, the given system will provide excellent operational and financial results in all significant indicators. The model has a reduction of 7.9% in NSF events that is realized to show improved accuracy in the prediction of overdraft risk and the minimization of unnecessary declines. It also allows approving about 10 million transactions, which demonstrates the greater efficiency of systems and the enhanced experience of the members. The 97% recovery in 15 days is a strong improvement in the repayment performance. More than that, the system leads to increased participation of members, as 28% of qualified users subscribe to the overdraft service. Finally, incremental interchange increase by 2% indicates quantifiable revenue improvements due to improved decisions of approvals. On the whole, the outcomes of these studies confirm the efficiency of the given strategy.
References
[1] L. Alessi and C. Detken, “Identifying excessive credit growth and leverage,” Journal of Financial Stability, vol. 35, pp. 215–225, 2018.
[2] L. Alessi and R. Savona, “Machine learning for financial stability,” in Data Science for Economics and Finance: Methodologies and Applications, S. Consoli, D. R. Recupero, and M. Saisana, Eds. Cham, Switzerland: Springer, 2021, pp. 65–87.
[3] G. Gopinath, T. Adrian, and M. Weeks-Brown, Reimagining Debt Management in the Digital Age. Washington, DC: International Monetary Fund, 2022.
[4] M. Gonzalez, “Rethinking financial distress: A public health approach to small business solvency,” Harvard Business Review, 2022.
[5] J. Kaszowska-Mojsa and M. Pipen, “Macroprudential policy in a heterogeneous environment—An application of agent-based approach in systemic risk modeling,” Entropy, vol. 22, no. 2, p. 129, 2020.
[6] Z. Hellman and R. Peretz, “A survey on entropy and economic behaviour,” Entropy, vol. 22, no. 2, p. 157, 2020.
[7] S. Mishra, D. Mishra, K. Mallick, G. H. Santra, and S. Kumar, “A novel borda count-based feature ranking and feature fusion strategy to attain effective climatic features for rice yield production,” Informatica, vol. 45, no. 1, pp. 13–32, 2021.
[8] T. Fischer and C. Krauss, “Deep learning with long short-term memory networks for financial market predictions,” European Journal of Operational Research, vol. 270, no. 2, pp. 654–669, 2018.
[9] A. Constantin, T. A. Peltonen, and P. Sarlin, “Network linkages to predict bank distress,” Journal of Financial Stability, vol. 35, pp. 226–241, 2018.
[10] A. Samitas, E. Kampouris, and D. Kenourgios, “Machine learning as an early warning system to predict financial crisis,” International Review of Financial Analysis, vol. 71, p. 101507, 2020.
[11] B. Ben Lahouel, L. Taleb, and M. Kossai, “Nonlinearities between bank stability and income diversification: A dynamic network data envelopment analysis approach,” Expert Systems with Applications, vol. 207, p. 117776, 2022.
[12] P. G. Coulombe, M. Leroux, D. Stevanovic, and S. Surprenant, “How is machine learning useful for macroeconomic forecasting?,” Journal of Applied Econometrics, vol. 37, no. 5, pp. 920–964, 2022.
