Journal of Cybersecurity and Information Management JCIM 2690-6775 2769-7851 10.54216/JCIM https://www.americaspg.com/journals/show/3764 2019 2019 University of Sharjah, UAE; Tashkent state University of Economics, Uzbekistan Noura Noura College of Business Administration, American University of the Middle East, Kuwait Sally Afchal 3College of Business Administration, American University of the Middle East, Kuwait Nasser El El-Kanj Credit risk assessment along with delinquency management in banking receives substantial improvements from the introduction of Artificial Intelligence (AI) and behavioural insights. This research creates an extensive behavioural credit-scoring model through its discovery of crucial psychological characteristics including integrity and self-efficacy and locus of control and materialism that greatly affect credit default and wilful delinquency. A thorough evaluation of the predictive model occurs through logistic regression and confirmatory factor analysis (CFA) based analysis on 376 respondent data. Self-efficacy together with internal locus of control and materialism demonstrate significant power as predictors for credit risk and the willingness of individuals to default voluntarily is directly influenced by integrity and self-esteem. The ability of Artificial intelligence approaches to forecasting depends on behavioural constructs to optimize precision accuracy, reduce credit risk estimation errors, and provide opportunities for early prevention. The model delivers 92.1% accurate Default Risk classifications together with 91.0% precise predictions for Liquidity Risk while maintaining a Default Risk AUC-ROC measure of 0.96, which signifies its advanced predictive capabilities. The research demonstrates that artificial intelligence alongside behavioural credit scoring systems can enhance financial lending decisions while stabilizing credit markets. 2025 2025 282 300 10.54216/JCIM.160120 https://www.americaspg.com/articleinfo/2/show/3764