An Adaptive Risk-Aware Machine Learning Framework for Cost-Effective Regression Test Case Prioritization

Regression testing is essential for identifying defects after software changes, but running all test cases can be time-consuming and costly. This paper proposes an Adaptive Risk-Aware Machine Learning Framework for Cost-Effective Regression Test Case Prioritization. The framework uses a Random Forest classifier to predict test case risk based on change impact, historical failures, code coverage, execution cost, and recent results. It dynamically prioritizes test cases using predicted risk, execution cost, and feedback from prior executions. We evaluated the approach using APFD, APFDc, fault detection rate, and execution cost. Experimental results show an APFD of 0.7173 and an APFDc of 0.7987, demonstrating improved test case prioritization compared with the selected baseline techniques.