David Bowes, Tracy Hall, Mark Harman, Yue Jia, Federica Sarro, and Fan Wu

We introduce mutation-aware fault prediction, which leverages additional guidance from metrics constructed in terms of mutants and the test cases that cover and detect them. Mutation-aware fault prediction can significantly (p ≤ 0.05) improve fault prediction performance. We report the results of 12 sets of experiments, applying 4 different predictive modelling techniques to 3 large real-world systems (both open and closed source). Mutation metrics lie in the top 5% most frequently relied upon defect predictors in 10 of the 12 sets of experiments, and provide the majority of the top ten defect predictors in 9 of the 12 sets of experiments.