Evaluating defect prediction approaches: a benchmark and an extensive comparison

By Marco D'Ambros, Michele Lanza, Romain Robbes. Empirical Software Engineering, 2011

608 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/ba98d43080bd0eeecba24c3124d63216c78494b8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Ahmed E. Hassan
2. Chakkrit Kla Tantithamthavorn
3. Ken-ichi Matsumoto
4. Shane McIntosh
5. Jaechang Nam
6. Tim Menzies
7. Wei Fu
8. David Lo

In Information Systems

1. Chakkrit Kla Tantithamthavorn
2. Ken-ichi Matsumoto
3. Ahmed E. Hassan
4. Shane McIntosh
5. Jaechang Nam
6. David Lo
7. Wei Fu
8. Lin Tan

In Software

1. Chakkrit Kla Tantithamthavorn
2. Ahmed E. Hassan
3. Ken-ichi Matsumoto
4. Shane McIntosh
5. Jaechang Nam
6. Lin Tan
7. Sunghun Kim
8. David Lo

Citations in the corpus

• Deep Learning for Just-in-Time Defect Prediction (2015, methodology): “present a benchmark for defect prediction and provide an extensive comparison of well-known approaches used for defect prediction in their survey [4].”
• An Empirical Comparison of Model Validation Techniques for Defect Prediction Models (2017, methodology): “Model performance is used to (1) indicate how well a model will perform on unseen data [22, 25, 65, 83, 113, 121]; (2) select the top-performing prediction model [36, 54, 62, 73, 77, 107, 115]; and (3) combine several prediction models [7, 91, 111, 117].”
• The Impact of Automated Parameter Optimization on Defect Prediction Models (2018, unknown): “[23, 24], and 3 datasets as provided by Zimmermann et al.”
• Heterogeneous Defect Prediction (2015, background): “To address the limitation, we propose heterogeneous defect prediction (HDP) to predict defects across projects with heterogeneous metric sets.”
• An empirical study on software defect prediction with a simplified metric set (2014, methodology): “a Firefox and Linux kernel. The models using all the three types of metrics together predicted over 80% of the known vulnerable files with less than 25% false positives for both projects. Marco et al. [34] conducted three experiments on five systems with process metrics, previous defects, source code ”
• Automated Parameter Optimization of Classification Techniques for Defect Prediction Models (2016, methodology): “[6, 7], and 3 are provided by Zimmermann et al.”
• The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models (2018, unknown): “[14, 15], and 3 datasets are 0 5 10 15 20 25 30 35”
• Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models (2015, methodology): “To perform defect prediction studies [21, 58], researchers have explored the use of various classification techniques to train defect prediction models [12, 34].”
• A Novel Neural Source Code Representation Based on Abstract Syntax Tree (2019, unknown): “defect prediction [7], [8] and code summarization [9], [10] have been proposed to improve software development and maintenance.”