Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Defect is Being Born: How Close Are We? A Time Sensitive Forecasting Approach

Mikel Robredo, Matteo Esposito, Fabio Palomba, Rafael Peñaloza, Valentina Lenarduzzi

TL;DR

This work tackles the problem of predicting defect proneness on a time scale, aiming to forecast defect density and signaling early indicators before defects arise. It compares Time Series Analysis, Bayesian inference, and Transformer-based models to provide probabilistic, time-aware estimates of defect occurrence, supported by a rigorous empirical design using the SQuaD dataset. By analyzing horizon-length effects and identifying the most informative software metrics, the study seeks to enhance proactive quality assurance and maintenance planning. The planned replication framework and ablation analyses further contribute to the robustness and practical relevance of time-sensitive defect forecasting in open-source software.

Abstract

Background. Defect prediction has been a highly active topic among researchers in the Empirical Software Engineering field. Previous literature has successfully achieved the most accurate prediction of an incoming fault and identified the features and anomalies that precede it through just-in-time prediction. As software systems evolve continuously, there is a growing need for time-sensitive methods capable of forecasting defects before they manifest. Aim. Our study seeks to explore the effectiveness of time-sensitive techniques for defect forecasting. Moreover, we aim to investigate the early indicators that precede the occurrence of a defect. Method. We will train multiple time-sensitive forecasting techniques to forecast the future bug density of a software project, as well as identify the early symptoms preceding the occurrence of a defect. Expected results. Our expected results are translated into empirical evidence on the effectiveness of our approach for early estimation of bug proneness.

A Defect is Being Born: How Close Are We? A Time Sensitive Forecasting Approach

TL;DR

This work tackles the problem of predicting defect proneness on a time scale, aiming to forecast defect density and signaling early indicators before defects arise. It compares Time Series Analysis, Bayesian inference, and Transformer-based models to provide probabilistic, time-aware estimates of defect occurrence, supported by a rigorous empirical design using the SQuaD dataset. By analyzing horizon-length effects and identifying the most informative software metrics, the study seeks to enhance proactive quality assurance and maintenance planning. The planned replication framework and ablation analyses further contribute to the robustness and practical relevance of time-sensitive defect forecasting in open-source software.

Abstract

Background. Defect prediction has been a highly active topic among researchers in the Empirical Software Engineering field. Previous literature has successfully achieved the most accurate prediction of an incoming fault and identified the features and anomalies that precede it through just-in-time prediction. As software systems evolve continuously, there is a growing need for time-sensitive methods capable of forecasting defects before they manifest. Aim. Our study seeks to explore the effectiveness of time-sensitive techniques for defect forecasting. Moreover, we aim to investigate the early indicators that precede the occurrence of a defect. Method. We will train multiple time-sensitive forecasting techniques to forecast the future bug density of a software project, as well as identify the early symptoms preceding the occurrence of a defect. Expected results. Our expected results are translated into empirical evidence on the effectiveness of our approach for early estimation of bug proneness.
Paper Structure (22 sections, 2 figures, 2 tables)

This paper contains 22 sections, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Software Defect Prediction
  4. Retrospective inspection of defects life cycle
  5. Time-Aware Analysis
  6. Time Series Analysis Approaches
  7. Bayesian approaches
  8. Transformer-based approaches
  9. Empirical Study Design
  10. Goal and Research Questions
  11. Study Context
  12. Variables
  13. Dependent variable
  14. Independent variables
  15. Study Execution
  16. ...and 7 more sections

Figures (2)

  • Figure 1: Overview of the study design (SQuaD: Software Quality Dataset)
  • Figure 2: Example of the life-cycle of a defect: Affected Version (AV), Injection Version (IV), defect Fixing Version (FV), defect Fixing commit (C$_i$). (j, y, z: Commit observation points)