ISSN Approved Journal || eISSN: 2582-8185 || CODEN: IJSRO2 || Impact Factor 8.2 || Google Scholar and CrossRef Indexed
Fast Publication within 48 hours || Low Article Processing Charges || Peer Reviewed and Referred Journal || Free Certificate
Credit scoring with AI: A comparative analysis of traditional vs. machine learning approaches
Independent Researcher, USA.
Review
International Journal of Science and Research Archive, 2022, 07(02), 716-723.
Article DOI: 10.30574/ijsra.2022.7.2.0300
Publication history:
Received on 02 November 2022; revised on 16 December 2022; accepted on 18 December 2022
Abstract:
Over time our financial industry changed because artificial intelligence and machine learning systems now determine creditworthiness better. Because they both meet specific requirement needs and offer easy understanding traditional credit scoring processes remain prevalent. Traditionally used credit scoring models need formatted past data to function so they cannot adjust quickly to fresh financial behavior. AI systems use a wide range of available transactional and alternative financial data to predict better and reach more customers effectively. This research helps people understand the main benefits and weaknesses of both classic and AI-based credit scoring tools in financial market operations. Computers show better accuracy than classic methods at finding credit risks and handling requests immediately. To make ethical financial decisions we need to solve problems with algorithms that favor certain customers and provide clear model details and reputation help. The study recommends that organizations use Artificial Intelligence appropriately to gain its benefits plus sustain fair and responsible credit decision making. Researchers should develop mixed methods that connect existing statistical models with artificial intelligence to make better credit risk judgments and give people without accounts better opportunities.
Keywords:
Credit Scoring; Artificial Intelligence; Machine Learning; Predictive Analytics; Financial Inclusion; Algorithmic Bias; Explainable AI; Credit Risk Assessment; Regulatory Compliance; Alternative Data Sources
Full text article in PDF:
Copyright information:
Copyright © 2022 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0
