Investigating the accuracy of credit bureau data in predicting borrowers' repayment of consumer loans in Nigeria

Adedeji Olowe; Adedeji Olowe

doi:10.3934/DSFE.2026002

Data Science in Finance and Economics

2026, Volume 6, Issue 1: 31-57. doi: 10.3934/DSFE.2026002

Previous Article Next Article

Research article

Investigating the accuracy of credit bureau data in predicting borrowers' repayment of consumer loans in Nigeria

Adedeji Olowe ^,

Lendsqr, Inc. 2055 Limestone Rd, Ste 200C Wilmington, Delaware 19808, USA

Received: 27 March 2025 Revised: 30 August 2025 Accepted: 12 November 2025 Published: 14 January 2026
JEL Codes: G21, G17

Consumer lending, especially microloans, is a critical component of financial inclusion and economic growth. However, the increasing reliance on credit bureau data to assess borrowers' repayment capabilities raises questions about its predictive accuracy. In this study, we evaluated the effectiveness of credit bureau data in predicting loan repayment behavior using a dataset from First Central, a Nigerian credit bureau, and Irorun, a digital lending institution in Nigeria. A total of 3,741 loan applicants, aged 21 to 60, were analyzed using traditional statistical tools and machine learning (ML) models, including logistic regression, random forests, and gradient boosting. Our results indicated that while credit bureau data provides some predictive insights, its standalone accuracy is limited due to inconsistencies in borrower credit histories and incomplete data reporting. Correlation analyses show weak associations between borrower-reported and bureau-reported overdue loan records and repayment outcomes, with Cramer's V values below 0.05. ML models, particularly gradient boosting, outperformed traditional statistical approaches, achieving an AUC-ROC of 0.77, highlighting the potential of advanced algorithms in credit risk assessment. Our findings suggest that integrating alternative borrower data, such as utility bill payments and digital transaction records, could enhance credit risk modeling. The study emphasizes the need for improved credit reporting accuracy and regulatory measures to ensure comprehensive borrower profiles. Enhancing predictive models with supplementary data sources can mitigate default risks and promote responsible lending, leading to greater financial inclusion in Nigeria.
- credit bureau data,
- loan repayment,
- machine learning,
- financial inclusion,
- digital lending,
- microloans,
- Nigeria
Citation: Adedeji Olowe. Investigating the accuracy of credit bureau data in predicting borrowers' repayment of consumer loans in Nigeria[J]. Data Science in Finance and Economics, 2026, 6(1): 31-57. doi: 10.3934/DSFE.2026002

Related Papers:

Abstract

Consumer lending, especially microloans, is a critical component of financial inclusion and economic growth. However, the increasing reliance on credit bureau data to assess borrowers' repayment capabilities raises questions about its predictive accuracy. In this study, we evaluated the effectiveness of credit bureau data in predicting loan repayment behavior using a dataset from First Central, a Nigerian credit bureau, and Irorun, a digital lending institution in Nigeria. A total of 3,741 loan applicants, aged 21 to 60, were analyzed using traditional statistical tools and machine learning (ML) models, including logistic regression, random forests, and gradient boosting. Our results indicated that while credit bureau data provides some predictive insights, its standalone accuracy is limited due to inconsistencies in borrower credit histories and incomplete data reporting. Correlation analyses show weak associations between borrower-reported and bureau-reported overdue loan records and repayment outcomes, with Cramer's V values below 0.05. ML models, particularly gradient boosting, outperformed traditional statistical approaches, achieving an AUC-ROC of 0.77, highlighting the potential of advanced algorithms in credit risk assessment. Our findings suggest that integrating alternative borrower data, such as utility bill payments and digital transaction records, could enhance credit risk modeling. The study emphasizes the need for improved credit reporting accuracy and regulatory measures to ensure comprehensive borrower profiles. Enhancing predictive models with supplementary data sources can mitigate default risks and promote responsible lending, leading to greater financial inclusion in Nigeria.

References

[1]	Agwu ME (2021) Can technology bridge the gap between rural development and financial inclusions? Technol Anal Strateg 33: 123–133. https://doi.org/10.1080/09537325.2020.1795111 doi: 10.1080/09537325.2020.1795111
[2]	Ajzen I (1991) The theory of planned behavior. Organ Behav Hum Decis Process 50: 179–211. https://doi.org/10.1016/0749-5978(91)90020-t doi: 10.1016/0749-5978(91)90020-t
[3]	Allen F, Demirgüç-Kunt A, Klapper L, et al. (2016) The foundations of financial inclusion: Understanding ownership and use of formal accounts. J Financ Intermed 27: 1–30. https://doi.org/10.1016/j.jfi.2015.12.003 doi: 10.1016/j.jfi.2015.12.003
[4]	Altman EI (1968) Financial ratios, discriminant analysis, and the prediction of corporate bankruptcy. J Financ 23: 589–609. http://dx.doi.org/10.1111/j.1540-6261.1968.tb00843.x doi: 10.1111/j.1540-6261.1968.tb00843.x
[5]	Avery RB, Calem PS, Canner GB (2004) Credit report accuracy and access to credit. Fed Reserve Bull 90: 297. https://doi.org/10.17016/BULLETIN.2004.90-3-2 doi: 10.17016/BULLETIN.2004.90-3-2
[6]	Baesens B, Roesch D, Scheule H (2016) Credit Risk Analytics: Measurement Techniques, Applications, and Examples in SAS. Wiley. https://doi.org/10.1002/9781119449560
[7]	Barboza F, Kimura H, Altman E (2017) Machine Learning Models and Bankruptcy Prediction. Expert Syst Appl 83: 405–417. https://doi.org/10.1016/j.eswa.2017.04.006 doi: 10.1016/j.eswa.2017.04.006
[8]	Bhandary R, Ghosh BK (2025) Credit Card Default Prediction: An Empirical Analysis on Predictive Performance Using Statistical and Machine Learning Methods. J Risk Financ Manag 18: 23. https://doi.org/10.3390/jrfm18010023 doi: 10.3390/jrfm18010023
[9]	Beck T, Levine R, Loayza N (2000) Finance and the sources of growth. J Financ Econ 58: 261–300. https://doi.org/10.1016/S0304-405X(00)00072-6 doi: 10.1016/S0304-405X(00)00072-6
[10]	Becker G (1964) Human Capital: A Theoretical and Empirical Analysis, with Special Reference to Education. Columbia University Press, New York.
[11]	Central Bank of Nigeria (2022) Financial stability report. Available from: https://www.cbn.gov.ng.
[12]	Chen H (2022) Prediction and Analysis of Financial Default Loan Behavior Based on Machine Learning Model. Comput Intell Neurosci 20: 7907210. https://doi.org/10.1155/2022/7907210 doi: 10.1155/2022/7907210
[13]	Chibba M (2009) Financial inclusion, poverty reduction and the millennium development goals. Eur J Dev Res 21: 213–230. https://doi.org/10.1057/ejdr.2008.17 doi: 10.1057/ejdr.2008.17
[14]	Cohen M (2007) Consumer credit, household financial management, and sustainable consumption. Int J Consum Stud 31: 57–65. https://doi.org/10.1111/j.1470-6431.2005.00485.x doi: 10.1111/j.1470-6431.2005.00485.x
[15]	Darwish JA (2025) Optimization and prediction of corporate credit rating through advanced feature selection based on AI and deep learning. Alex Eng J 127: 586–594. https://doi.org/10.1016/j.aej.2025.05.043. doi: 10.1016/j.aej.2025.05.043
[16]	Demirgüç-Kunt A, Klapper L, Singer D, et al. (2018) The Global Findex Database 2017: Measuring Financial Inclusion and the Fintech Revolution. World Bank Publications, World Bank, Washington, DC. http://dx.doi.org/10.1596/978-1-4648-1259-0
[17]	Demirgüç-Kunt A, Klapper L, Singer D (2017) Financial inclusion and inclusive growth: A review of recent empirical evidence. Policy Research Working Paper 8040. World Bank Group. https://doi.org/10.1596/1813-9450-8040
[18]	Demirhan H (2024) Financial Anomalies and Creditworthiness: A Python-Driven Machine Learning Approach Using Mahalanobis Distance for ISE-Listed Companies in the Production and Manufacturing Sector. J Financ Risk Mana 13: 1–14. https://doi.org/10.4236/jfrm.2024.131001 doi: 10.4236/jfrm.2024.131001
[19]	Dev M (2006) Financial Inclusion: Issues and Challenges. Econ Polit Weekly 41: 4310–4313. http://www.jstor.org/stable/4418799
[20]	Dinh TN, Thanh BP (2022) Loan Repayment Prediction Using Logistic Regression Ensemble Learning with Machine Learning Algorithms. 9th International Conference on Soft Computing & Machine Intelligence (ISCMI), Toronto, ON, Canada, 79–85, https://doi.org/10.1109/ISCMI56532.2022.10068483
[21]	Dulloo R (2021) Microfinance: Fostering inclusive growth in India. Pac Bus Rev Int 13: 79–87.
[22]	Dyché J, Levy E (2006) Customer data integration: Reaching a single version of the truth, 7 John Wiley & Sons.
[23]	Ediagbonya V, Tioluwani C (2023) The role of fintech in driving financial inclusion in developing and emerging markets: issues, challenges and prospects. Technol Sustain 2: 100–119. https://doi.org/10.9790/5933-1506014749 doi: 10.9790/5933-1506014749
[24]	EFInA (2021) Digital financial services in Nigeria: Expanding access to credit. EFInA Report.
[25]	Ehiedu VC, Onuorah AC, Chigbo N (2022) Innovative banking models and banks fragility in post covid-19 era in Nigeria. Int J Acad Account Financ Manag Res 6: 91–100. Available from: http://ijeais.org/wp-content/uploads/2022/5/IJAAFMR220509.pdf.
[26]	Ezie O, Oniore J, Ajaegbu PC (2023) Financial Technology and Economic Growth in Nigeria: 2012Q1–2022Q4. Am J Financ Technol Innov 1: 35–45. https://doi.org/10.54536/ajfti.v1i1.2325 doi: 10.54536/ajfti.v1i1.2325
[27]	Falaiye T, Odeyemi O, Ajayi-Nifise A, et al. (2024) A review of microfinancing's role in entrepreneurial growth in African Nations. Int J Sci Res Arch 11: 1376–1387. https://doi.org/10.30574/ijsra.2024.11.1.0229 doi: 10.30574/ijsra.2024.11.1.0229
[28]	Fanta AB, Mutsonziwa K (2021) Financial Literacy as a Driver of Financial Inclusion in Kenya and Tanzania. J Risk Financ Manag 14: 45–63. https://doi.org/10.3390/jrfm14110561 doi: 10.3390/jrfm14110561
[29]	Frank D, Bhandary R, Prabhu SK (2024) Higher Education Loan Schemes Across the Globe: A Systematic Review on the Utility Derived and Burden Associated with Educational Debt. J Risk Financ Manag 17: 566. https://doi.org/10.3390/jrfm17120566 doi: 10.3390/jrfm17120566
[30]	Hand DJ, Henley WE (1997) Statistical classification methods in consumer credit scoring: A review. J R Stat Soc A 160: 523–541. https://doi.org/10.1111/j.1467-985X.1997.00078.x doi: 10.1111/j.1467-985X.1997.00078.x
[31]	Iganiga BO (2008) Much Ado About Nothing: The Case of the Nigerian Microfinance Policy Measures, Institutions, and Operations. J Soc Sci 17: 89–101. https://doi.org/10.1080/09718923.2008.11892638 doi: 10.1080/09718923.2008.11892638
[32]	International Finance Corporation (2020) Digital financial services in Africa: What COVID-19 changed. IFC Working Paper.
[33]	Johnstone DB, Marcucci PN (2010) Financing Higher Education Worldwide: Who Pays? Who Should Pay? Johns Hopkins University Press. https://doi.org/10.56021/9780801894572
[34]	Kama U, Adigun M (2013) Financial Inclusion in Nigeria: Issues and Challenges. Central Bank of Nigeria, Abuja, Occasional Paper No. 45. https://doi.org/10.2139/ssrn.2365209
[35]	Kashim AR (2018) Exploring the Strategies for Accessing Microloans Used by Small and Medium Enterprises. Doctoral Dissertation. Walden University. Available from: https://scholarworks.waldenu.edu/dissertations.
[36]	Kola-Oyeneyin E, Kuyoro M, Olanrewaju T (2020) Harnessing Nigeria's fintech potential: How stakeholders could position the fintech sector for growth now and beyond the crisis. McKinsey & Company. Available from: http://dln.jaipuria.ac.in: 8080/jspui/bitstream/123456789/10809/1/Harnessing-nigerias-fintech-potential.pdf.
[37]	Lemieux ME, Reveles XT, Rebeles J, et al. (2023) Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning. Respir Res 24: 23. https://doi.org/10.1186/s12931-023-02327-3 doi: 10.1186/s12931-023-02327-3
[38]	Li Y, Peng J (2023) Digital financial inclusion and welfare: Effect, mechanism and imbalance. PLoS ONE 18: e0278956. https://doi.org/10.1371/journal.pone.0278956 doi: 10.1371/journal.pone.0278956
[39]	Mallinguh E, Wasike C (2025) An Empirical Analysis of Loan Repayment Behavior and Default Rates on Digital Lending Platforms: Evidence from an Emerging Market. Qeios 7. https://doi.org/10.32388/DKJLUJ.2 doi: 10.32388/DKJLUJ.2
[40]	Melton RB (1965) Schultz's Theory of "Human Capital." Southwest Soc Sci Q 46: 264–272. Available from: http://www.jstor.org/stable/42880285.
[41]	Meng K, Mahapatra MS, Xiao JJ (2025) Artificial Intelligence and Consumer Financial Behavior: A Systematic Literature Review and Agenda for Future Research. J Consum Behav 24: 1755–1786. https://doi.org/10.1002/cb.2497. doi: 10.1002/cb.2497
[42]	Nazareth N, Reddy YVR (2023) Financial applications of machine learning: A literature review. Expert Syst Appl 219: 119640. https://doi.org/10.1016/j.eswa.2023.119640 doi: 10.1016/j.eswa.2023.119640
[43]	Nguyen QG, Nguyen LH, Hosen MM, et al. (2025) Enhancing Credit Risk Management with Machine Learning: A Comparative Study of Predictive Models for Credit Default Prediction. Am J Appl Sci 7: 21–30. https://doi.org/10.37547/tajas/Volume07Issue01-04 doi: 10.37547/tajas/Volume07Issue01-04
[44]	Nnaomah UI, Aderemi S, Olutimehin DO, et al. (2024) Digital banking and financial inclusion: a review of practices in the USA and Nigeria. Financ Account Res J 6: 463–490. https://doi.org/10.51594/farj.v6i3.971 doi: 10.51594/farj.v6i3.971
[45]	Okoroafor SN (2024) Impact of COVID-19 on digital financial inclusion in Nigeria: A study of IMO STATE in the South-East geopolitical zone. J Acad Financ 15: 120–139. https://doi.org/10.59051/joaf.v15i3.699 doi: 10.59051/joaf.v15i3.699
[46]	Shen H, Ziderman A (2009) Student loans repayment and recovery: international comparisons. High Educ 57: 315–333. https://doi.org/10.1007/s10734-008-9146-0 doi: 10.1007/s10734-008-9146-0
[47]	Soetan TO, Mogaji E, Nguyen NP (2021) Financial services experience and consumption in Nigeria. J Serv Mark 35: 947–961. https://doi.org/10.1108/JSM-07-2020-0280 doi: 10.1108/JSM-07-2020-0280
[48]	Valecha H, Varma A, Khare I, et al. (2018) Prediction of Consumer Behaviour using Random Forest Algorithm. 5th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), Gorakhpur, India, 1–6, https://doi.org/10.1109/UPCON.2018.8597070
[49]	Wang H, Du X, Ge C, et al. (2024) Does digital credit alleviate household income vulnerability? Pac-Basin Financ J 88: 102542. https://doi.org/10.1016/j.pacfin.2024.102542 doi: 10.1016/j.pacfin.2024.102542
[50]	Yadav R, Awasthi A (2024) Predicting Corporate Bankruptcy: A Comparative Analysis of Machine Learning. Models. Int Res J Modern Eng Technol Sci 06. https://www.doi.org/10.56726/IRJMETS53108

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)