The influence of machine learning algorithms on credit scoring strategy in FinTech: A proposal for comparative research
Download This Article
Puteri N. E. Nohuddin , Sami Emadeddin Alajlani
, Lawal O. Yesufu
, Nora Azima Noordin
, Malik Muhammad Sheheryar Khan
, Sergio Tirado Ramos
This work is licensed under a Creative Commons Attribution 4.0 International License.
Abstract
Financial technology (FinTech) and data analytics raise the bar on the level of accuracy, inclusiveness, and effective risk management compared to conventional models. Markov et al. (2022) and Quach et al. (2022) present a comparative study related to data analytics and machine learning algorithms of credit score modelling between traditional financial institutions and FinTech startups. The paper discusses the consequences of such models for financial inclusion and risk management. This research, based on a mixed-method approach that combines quantitative analysis of credit scoring model performance with qualitative insights from interviews with industry experts, demonstrates the key differences in effectiveness and efficiency between the two sectors. Whereas traditional banks often rely on historical financial data, FinTech companies use alternative data sources supplemented by advanced analytics, promising speedier and more inclusive credit decisions. Furthermore, the paper develops implications for financial inclusions and risk management, which imply that FinTech credit scoring might act as a conduit to reaching out with credit to the relatively unserved parts of the population, while engendering challenges like algorithmic bias and regulatory oversight. This paper develops a very elaborate view of the current financial landscape and hence underlining practical and theoretical insights into the study, while giving some recommendations to traditional financial institutions, policymakers, and even the FinTech firms themselves.
Keywords: Financial Technology, Data Analytics, Machine Learning, Credit Scoring, Insights
Authors’ individual contribution: Conceptualization — P.N.E.N., S.E.A., and L.O.Y.; Methodology — P.N.E.N. and N.A.N.; Validation — P.N.E.N., S.E.A., and L.O.Y.; Formal Analysis — P.N.E.N. and N.A.N.; Investigation — P.N.E.N., S.E.A., and M.M.S.K.; Writing — Original Draft — P.N.E.N., S.E.A., and L.O.Y.; Writing — Review & Editing — P.N.E.N., N.A.N., and S.T.R.; Visualization — M.M.S.K. and S.T.R.; Supervision — P.N.E.N.
Declaration of conflicting interests: The Authors declare that there is no conflict of interest.
JEL Classification: G21, G32, O33, D14
Received: 14.08.2024
Revised: 22.11.2024; 02.06.2025
Accepted: 30.06.2025
Published online: 04.07.2025
How to cite this paper: Nohuddin, P. N. E., Alajlani, S. E., Yesufu., L. O., Noordin, N. A., Khan, M. M. S., & Tirado Ramos, S. (2025). The influence of machine learning algorithms on credit scoring strategy in FinTech: A proposal for comparative research. Corporate & Business Strategy Review, 6(3), 96–104. https://doi.org/10.22495/cbsrv6i3art9