System regression test planning with a fuzzy expert system

An effective system testing activity for consecutive releases of very large software systems depends considerably on the selection of test cases for execution. From a practical point of view, it is not feasible to run all possible test cases because of the real-world constraints of limited time, human and monetary resources. While existing techniques for test case selection provide methods to limit the growth of the number of test cases with software evolution, many of them are based on the assumption that source code analysis is available. Very few works have explored the problem of test case selection given the constraint that source code analysis is not available. We propose fuzzy expert systems as an effective solution to the problem. Fuzzy expert systems have the ability to emulate fuzzy human reasoning and judgment processes. The proposed fuzzy expert system identifies potentially critical test cases for system test by correlating knowledge represented by one or more of the following: customer profile, analysis of past test case results, system failure rate, and change in system architecture. We piloted this fuzzy expert system in a large telecommunications system and the results show that test effectiveness and efficiency is significantly improved.