Towards a Software Change Classification System: A Rough Set Approach

The basic contribution of this paper is the presentation of two methods that can be used to design a practical software change classification system based on data mining methods from rough set theory. These methods incorporate recent advances in rough set theory related to coping with the uncertainty in making change decisions either during software development or during post-deployment of a software system. Two well-known software engineering data sets have been used as means of benchmarking the proposed classification methods, and also to facilitate comparison with other published studies on the same data sets. Two technologies in computation intelligence (CI) are used in the design of the software change classification systems described in this paper, namely, rough sets (a granular computing technology) and genetic algorithms. Using 10-fold cross validated paired t-test, this paper also compares the rough set classification learning method with the Waikato Environment for Knowledge Analysis (WEKA) classification learning method. The contribution of this paper is the presentation of two models for software change classification based on two CI technologies.