Researcher Bias: The Use of Machine Learning in Software Defect Prediction

By Martin J. Shepperd, David Bowes, Tracy Hall. IEEE Transactions on Software Engineering, 2014

375 citations recorded by the source corpus.

How researchers see this paper

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

Automated Parameter Optimization of Classification Techniques for Defect Prediction Models (2016, background): “0 classification technique is the most influential parameter, while the winnow and model type parameters tend to have less of an impact.”
Online Defect Prediction for Imbalanced Data (2015, methodology): “We use the commonly used metrics [4], [40] to measure the results.”
Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models (2015, background): “Despite recent advances in machine learning, studies suggest that the classification technique used to train defect prediction models has little impact on its performance [34, 38, 56].”
The Impact of Automated Parameter Optimization on Defect Prediction Models (2018, positive): “[122], we includeMatthews Correlation Coefficient.”