Dynamic Prioritization of Test Cases for Regression Testing using Machine Learning

Test cases can be selected on the basis of various parameters i.e. importance, complexity, and prospective effect over the applications. Using these parameters, priority is assigned to each test case and these are executed in a particular sequence accordingly, to reveal the bugs in code. Researches have proposed various methods to achieve this goal this paper, presents a dynamic prioritization of test cases for regression testing using machine learning and its performance analysis using different algorithms and classifiers shows that its APFD (Average Perdition of Fault detection) is 0.589895, execution time is 2.410775, precision & recall is 1 (highest), f1-score is 0.97 (max) as compared to existing schemes.