Blogs (1) >>
ICSE 2019
Sat 25 - Fri 31 May 2019 Montreal, QC, Canada
Fri 31 May 2019 11:30 - 11:50 at Laurier - Defect Prediction Chair(s): Burak Turhan

Just-in-Time Software Defect Prediction (JIT-SDP) is an SDP approach that makes defect predictions at the software change level. Most existing JIT-SDP work assumes that the characteristics of the problem remain the same over time. However, JIT-SDP may suffer from class imbalance evolution. Specifically, the imbalance status of the problem (i.e., how much underrepresented the defect-inducing changes are) may be intensified or reduced over time. If occurring, this could render existing JIT-SDP approaches unsuitable, including those that re-build classifiers over time using only recent data. This work thus provides the first investigation of whether class imbalance evolution poses a threat to JIT-SDP. This investigation is performed in a realistic scenario by taking into account verification latency – the often overlooked fact that labeled training examples arrive with a delay. Based on 10 GitHub projects, we show that JIT-SDP suffers from class imbalance evolution, significantly hindering the predictive performance of existing JIT-SDP approaches. Compared to state-of-the-art class imbalance evolution learning approaches, the predictive performance of JIT-SDP approaches was up to 47.92% lower in terms of g-mean. Hence, it is essential to tackle class imbalance evolution in JIT-SDP. We therefore propose a novel class imbalance evolution approach for the specific context of JIT-SDP. While maintaining top ranked g-means, this approach managed to produce up to 12% more balanced recalls on the defect-inducing and clean classes than state-of-the-art class imbalance evolution approaches. We thus recommended it to avoid overemphasizing the defect-inducing class at the cost of too many false alarms in JIT-SDP.

Fri 31 May
Times are displayed in time zone: Eastern Time (US & Canada) change

11:00 - 12:30: Defect PredictionPapers / Journal-First Papers / Technical Track / New Ideas and Emerging Results at Laurier
Chair(s): Burak TurhanMonash University
11:00 - 11:10
Talk
Perceptions, Expectations, and Challenges in Defect PredictionJournal-First
Journal-First Papers
Zhiyuan WanZhejiang University, Xin XiaMonash University, Ahmed E. HassanQueen's University, David LoSingapore Management University, Jianwei Yin, Xiaohu Yang
11:10 - 11:30
Talk
Mining Software Defects: Should We Consider Affected Releases?Artifacts AvailableArtifacts Evaluated ReusableTechnical Track
Technical Track
Suraj YatishThe University of Adelaide, Jirayus JiarpakdeeMonash University, Patanamon ThongtanunamThe University of Melbourne, Chakkrit (Kla) TantithamthavornMonash University, Australia
11:30 - 11:50
Talk
Class Imbalance Evolution and Verification Latency in Just-in-Time Software Defect PredictionTechnical Track
Technical Track
George CabralUniversity of Birmingham, Leandro Minku , Emad ShihabConcordia University, Suhaib MujahidConcordia University
11:50 - 12:00
Talk
The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction ModelsJournal-First
Journal-First Papers
Chakkrit (Kla) TantithamthavornMonash University, Australia, Ahmed E. HassanQueen's University, Kenichi MatsumotoNara Institute of Science and Technology
Pre-print
12:00 - 12:10
Talk
On the Relative Value of Data Resampling Approaches for Software Defect PredictionJournal-First
Journal-First Papers
Kwabena E. BenninBlekinge Institute of Technology, SERL Sweden, Jacky Keung, Akito Monden
Authorizer link
12:10 - 12:20
Talk
Energy-Based Anomaly Detection A New Perspective for Predicting Software FailuresNIER Distinguished Paper AwardNIER
New Ideas and Emerging Results
Cristina MonniUniversità della Svizzera Italiana, Mauro PezzeUniversità della Svizzera italiana (USI) (Switzerland) and Università degli Studi di Milano Bicocca (Italy)
Pre-print
12:20 - 12:30
Talk
Discussion Period
Papers