Quantifying Learning Dynamics in Saudi Fintech Software Reliability: An Enhanced NHPP-SW Model for SAMA-Compliant Systems

الملخص

A In alignment with Saudi Arabia’s Vision 2030 and the Saudi Central Bank (SAMA) regulatory directives, the financial sector is undergoing rapid digital transformation, increasing the demand for reliable fintech software systems. This study introduces an Enhanced Schick-Wolverton Non-Homogeneous Poisson Process (NHPP-SW) model that integrates a learning parameter (α) to reflect organizational learning, coordination efficiency, and regulatory adaptation. Calibrated using simulated defect-arrival data representative of ten prominent Saudi fintech firms, the model parameters were estimated through nonlinear least-squares optimization via the Levenberg-Marquardt algorithm. Evaluation against standard reliability metrics including Root Mean Square Error (RMSE), Mean Square Error (MSE), and the Mean Value Function (MVF) demonstrates the model’s high predictive accuracy, with relative RMSE consistently below 5%. Beyond technical performance, the model offers practical value for financial institutions by enabling early detection of readiness for regulatory compliance, optimizing resource allocation for testing and quality assurance, and providing objective benchmarks for reliability growth. The results affirm the model’s utility as a strategic decision-support tool for enhancing software reliability and ensuring regulatory alignment within the evolving Saudi fintech landscape.