Learning a Classifier for Prediction of Maintainability based on Static Analysis Tools

Markus Schnappinger, Mohd Hafeez Osman, Alexander Pretschner, Arnaud Fietzke

Download the comprehensive research paper on predicting software maintainability using static analysis tools. This scholarly work, conducted by experts from the Technical University of Munich and itestra GmbH, meticulously examines source code from various projects. The study employs machine learning algorithms to forecast the maintainability of software classes based on code metrics. The findings reveal promising techniques for automated maintainability assessments, providing valuable insights for developers striving to maintain high-quality software systems. Access the full document to delve into the methodologies, results, and practical implications of this pioneering research.

2019 IEEE/ACM 27th INTERNATIONAL CONFERENCE ON PROGRAM COMPREHENSION (ICPC)

https://itestra.com/wp-content/uploads/2021/03/icpc-from-proceedings-1.pdf

Learning a Classifier for Prediction of Maintainability based on Static Analysis Tools