Thorough expert assessments are precise yet slow and expensive, whereas automated static analysis yields imprecise yet rapid feedback. Several machine learning approaches aim to integrate the advantages of both concepts. In contrast to most related work, the present study builds on a manually labeled and validated dataset. Prediction is done using static code metrics where we found simple structural metrics such as the size of a class and its methods to yield the highest predictive power towards maintainability. In sum, our models achieve the same level of prediction performance as an average human expert. In fact, the obtained accuracy and mean squared error outperform human performance.
Read the paper: https://doi.org/10.1145/3463274.3463315