The Need for a Fine-grained approach in Just-in-Time Defect Prediction

TL;DR

This paper highlights the importance of a fine-grained approach in Just-in-Time defect prediction, introduces a new dataset linking features with commits, and investigates feature gaps in existing methods to improve defect prediction accuracy.

Contribution

It proposes a fine-grained methodology for JIT defect prediction and provides a new dataset to facilitate research linking features with actual code commits.

Findings

Identification of feature gaps in existing JIT methods

Development of a new dataset linking features with commits

Emphasis on the need for a more detailed approach in defect prediction

Abstract

With software system complexity leading to the rise of software defects, research efforts have been done on techniques towards predicting software defects and Just-in-time (JIT) defect prediction which predicts whether a code change is defective. While using features to determine potentially defective code change, inspection effort is still significant. As code change can impact several files, we investigate an open source project to identify potential gaps with features in JIT perspective. In addition, with a lack of publicly available JIT dataset that link the features with actual commits, we also present a new dataset that can be utilized in JIT and semantic analysis.