Scoring models are widely renowned and used in financial organizations in a variety of fields, but most importantly – to predict and control credit risk. This article addresses practical problems of scorecards usage after its implementation. With time its predictive power tends to deteriorate, but not always it is applicable to completely rebuild the model fast enough due to lack of time/human/financial resources. Then cut-off, which was set when the scorecard was initially implemented, should be corrected to achieve optimal (i.e. cash-flow maximizing) performance. The literature on ways to maintain the existing model over time and manage the cut-offs is extremely scarce. The article is built on simple yet fundamental analytical explanations of scorecard performance dynamics, derived from practical experience. Results are backed by a numerical example, which shows the efficiency of different managerial decisions regarding cut-off setting in the paradox zone. The main conclusions are the following. In the most common case, the optimal reaction on model deterioration would be to counterintuitively narrow down the reject zone via cut-offs, which results in higher sales amount and even more increased risk ratios, but maximizes cash-flow in given conditions. This is the core of the scoring model deterioration paradox. It arises from the fact that when the scorecard deteriorates the high-risk segments of clients are actually becoming less risky and hence more profitable. This affects cut-offs, which must be applied to reject the riskiest loss-making segment of loan applications.
| Published in | International Journal of Finance and Banking Research (Volume 8, Issue 1) |
| DOI | 10.11648/j.ijfbr.20220801.16 |
| Page(s) | 39-47 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2022. Published by Science Publishing Group |
Credit Scoring, Scoring Model, Scorecard Lifecycle, Model Risk, Cut-offs
| [1] | Anderson, Raymond. 2007. The credit scoring toolkit, theory, and practice for retail credit risk. Management and decision automation, Oxford University Press, Oxford. |
| [2] | Board of Governors of the Federal Reserve System, 2011. Supervisory Guidance on Model Risk Management: SR Letter 11-7 Attachment. |
| [3] | Jung K. M., Thomas L. C., Mee Chi So. 2013. Time varying or static cut-offs for credit scorecards. Journal of the Operational Research Society, Palgrave Macmillan; The OR Society, vol. 64 (9), pages 1299-1306, September. |
| [4] | Jung K. M., Thomas L. C., Mee Chi So. 2015. When to rebuild or when to adjust scorecards [Link]. |
| [5] | Kelly, Mark Gerard. 1998. Tackling change and uncertainty in credit scoring. PhD thesis The Open University. |
| [6] | Kritzinger, Nico. 2017. Improving credit risk measurement and management: A new application of statistical techniques. Thesis submitted for the degree Philosophiae Doctor in Risk Analysis at the Potchefstroom Campus of the North-West University. October. |
| [7] | Kritzinger, N. & Van Vuuren, G. W., 2018. An optimized credit scorecard to enhance cut-off score determination. South African Journal of Economic and Management Sciences 21 (1), a1571. https://doi.org/10.4102/sajems.v21i1.1571. |
| [8] | Lewis E. M. 1992. An Introduction to Credit Scoring, 2nd Ed. Athena Press: San Rafael, CA. |
| [9] | López-Ratón M., Rodríguez-Álvarez M., Cadarso-Suárez C., Gude-Sampedro F., 2014. OptimalCutpoints: An R Package for Selecting Optimal Cutpoints in Diagnostic Tests. Journal of Statistical Software. October 2014, Volume 61, Issue 8. |
| [10] | Madzova Violeta, Ramadini Nehat. 2013. Can credit scoring models prevent default payments in the banking industry in the period of financial crisis? International Journal of Business and Technology. Volume 2, issue 1, article 5. November. |
| [11] | McNab H., Wynn A., 2000. Principles and Practice of Consumer Credit Risk Management. CIB Publishing, Canterbury. |
| [12] | Siddiqi, Naeem. 2006. Credit risk scorecards, developing and implementing intelligent credit scoring, John Wiley & Sons, Inc. Hoboken, NJ. |
| [13] | Thomas, L. C., 2009. Consumer Credit Models: Pricing, Profit, and Portfolios Oxford University Press. Oxford, UK. |
| [14] | Tikhonov Roman, Masyutin Aleksey, Anpilogov Vadim. 2019. Relationship between Credit risk management and financial performance: empirical evidence from microfinance banks in Kenya. Research Journal of Finance and Accounting. Vol. 7, No. 6. |
| [15] | Verstraeten G., D. Van den Poel. 2003. Quantifying credit-scoring performance. Transactions on Information and Communications Technologies. Volume 29, WIT Press. |
APA Style
Mykyta Voloshyn. (2022). The Paradox of Credit Scoring Model Deterioration. International Journal of Finance and Banking Research, 8(1), 39-47. https://doi.org/10.11648/j.ijfbr.20220801.16
ACS Style
Mykyta Voloshyn. The Paradox of Credit Scoring Model Deterioration. Int. J. Finance Bank. Res. 2022, 8(1), 39-47. doi: 10.11648/j.ijfbr.20220801.16
AMA Style
Mykyta Voloshyn. The Paradox of Credit Scoring Model Deterioration. Int J Finance Bank Res. 2022;8(1):39-47. doi: 10.11648/j.ijfbr.20220801.16
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ijfbr.20220801.16,
author = {Mykyta Voloshyn},
title = {The Paradox of Credit Scoring Model Deterioration},
journal = {International Journal of Finance and Banking Research},
volume = {8},
number = {1},
pages = {39-47},
doi = {10.11648/j.ijfbr.20220801.16},
url = {https://doi.org/10.11648/j.ijfbr.20220801.16},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijfbr.20220801.16},
abstract = {Scoring models are widely renowned and used in financial organizations in a variety of fields, but most importantly – to predict and control credit risk. This article addresses practical problems of scorecards usage after its implementation. With time its predictive power tends to deteriorate, but not always it is applicable to completely rebuild the model fast enough due to lack of time/human/financial resources. Then cut-off, which was set when the scorecard was initially implemented, should be corrected to achieve optimal (i.e. cash-flow maximizing) performance. The literature on ways to maintain the existing model over time and manage the cut-offs is extremely scarce. The article is built on simple yet fundamental analytical explanations of scorecard performance dynamics, derived from practical experience. Results are backed by a numerical example, which shows the efficiency of different managerial decisions regarding cut-off setting in the paradox zone. The main conclusions are the following. In the most common case, the optimal reaction on model deterioration would be to counterintuitively narrow down the reject zone via cut-offs, which results in higher sales amount and even more increased risk ratios, but maximizes cash-flow in given conditions. This is the core of the scoring model deterioration paradox. It arises from the fact that when the scorecard deteriorates the high-risk segments of clients are actually becoming less risky and hence more profitable. This affects cut-offs, which must be applied to reject the riskiest loss-making segment of loan applications.},
year = {2022}
}
TY - JOUR T1 - The Paradox of Credit Scoring Model Deterioration AU - Mykyta Voloshyn Y1 - 2022/02/09 PY - 2022 N1 - https://doi.org/10.11648/j.ijfbr.20220801.16 DO - 10.11648/j.ijfbr.20220801.16 T2 - International Journal of Finance and Banking Research JF - International Journal of Finance and Banking Research JO - International Journal of Finance and Banking Research SP - 39 EP - 47 PB - Science Publishing Group SN - 2472-2278 UR - https://doi.org/10.11648/j.ijfbr.20220801.16 AB - Scoring models are widely renowned and used in financial organizations in a variety of fields, but most importantly – to predict and control credit risk. This article addresses practical problems of scorecards usage after its implementation. With time its predictive power tends to deteriorate, but not always it is applicable to completely rebuild the model fast enough due to lack of time/human/financial resources. Then cut-off, which was set when the scorecard was initially implemented, should be corrected to achieve optimal (i.e. cash-flow maximizing) performance. The literature on ways to maintain the existing model over time and manage the cut-offs is extremely scarce. The article is built on simple yet fundamental analytical explanations of scorecard performance dynamics, derived from practical experience. Results are backed by a numerical example, which shows the efficiency of different managerial decisions regarding cut-off setting in the paradox zone. The main conclusions are the following. In the most common case, the optimal reaction on model deterioration would be to counterintuitively narrow down the reject zone via cut-offs, which results in higher sales amount and even more increased risk ratios, but maximizes cash-flow in given conditions. This is the core of the scoring model deterioration paradox. It arises from the fact that when the scorecard deteriorates the high-risk segments of clients are actually becoming less risky and hence more profitable. This affects cut-offs, which must be applied to reject the riskiest loss-making segment of loan applications. VL - 8 IS - 1 ER -
Information
Email: