Toward comprehensible software defect prediction models using fuzzy logic

Abstract

Software defect prediction is a discipline that predicts the defects proneness of future modules. Software metrics are used for this kind of predication. However, the predication metrics are associated with uncertainty, thus the metrics need to be expressed in linguistic terms to overcome ambiguity and uncertainty. Two types of knowledge are utilized as input to the prediction models: software metrics and expert's opinions. This paper proposes a framework for developing fuzzy logic-based software predication model using different set of software metrics. It aims to provide a generic set of metrics to be used for software defects prediction. The performance of the proposed Fuzzy-based models has been validated using real software projects data where Takagi-Sugeno fuzzy inference engine is used to predict software defects. Validation results are satisfactory.