Misclassification cost-sensitive fault prediction models

Abstract

Traditionally, software fault prediction models are built by assuming a uniform misclassification cost. In other words, cost implications of misclassifying a faulty module as fault free are assumed to be the same as the cost implications of misclassifying a fault free module as faulty. In reality, these two types of misclassification costs are rarely equal. They are project-specific, reflecting the characteristics of the domain in which the program operates. In this paper, using project information from a public repository, we analyze the benefits of techniques which incorporate misclassification costs in the development of software fault prediction models. We find that cost-sensitive learning does not provide operational points which outperform cost-insensitive classifiers. However, an advantage of cost-sensitive modeling is the explicit choice of the operational threshold appropriate for the cost differential.