The Probabilistic Bounds on the Feasibility of the Defect Prediction Models in Real-World Testing Environments

TL;DR

This paper investigates the real-world feasibility of software defect prediction models, providing probabilistic bounds to assess their practical applicability beyond theoretical development.

Contribution

It introduces probabilistic bounds to evaluate the feasibility of defect prediction models in real-world testing environments, addressing a key gap in existing research.

Findings

Provides probabilistic bounds for model feasibility

Bridges the gap between model development and real-world application

Offers a framework applicable to various machine learning domains

Abstract

The research on developing software defect prediction (SDP) models is targeted at reducing the workload on the tester and, thereby, the time spent on the targeted module. However, while a considerable amount of research has been done on developing prediction models or attempting to mitigate the related issues in developing prediction models, it is still unknown whether the developed prediction model really works in real-world testing environments or not. With this article, we bridge this research gap of finding the feasibility of the developed binary defect prediction model in the real-world testing environments. Because machine learning (ML) applications span over many domains, we hope this article may provide sufficient ground to do research on analysing the feasibility of developed prediction models in the related applications in real-time scenarios.