AI-driven predictive testing: Enhancing software reliability in high-stakes financial systems
Year: 2025
Type: article
Abstract: This article explores how AI-driven predictive testing is transforming software quality assurance in high-stakes financial systems. Traditional testing methods remain reactive, identifying defects only after they manifest, whereas predictive testing leverages machine learning to anticipate and prevent failures before they occur. The article examines the evolution from conventional to AI-powered testing approaches, detailing core components of predictive testing frameworks, including failure analysis using historical data, dynamic test case prioritization, and automated root cause analysis. Implementation strategies for financial institutions are discussed, focusing on integration with existing DevOps pipelines, data collection requirements, and balancing automation with human expertise. Real-world applications across high-frequency trading, wealth management, and loan processing demonstrate how these advanced testing methodologies enhance system reliability, regulatory compliance, and operational efficiency while significantly reducing financial risks.
Author: Palanisamy, Pradeepkumar
Institution: Anna University, Chennai
Language: English
Subfield: Software
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7085070964
FWCI:
Cites:
Cited by:
Related to: