January 18, 2021
An open-access paper titled “Enhanced Bug Prediction in JavaScript Programs with Hybrid Call-Graph Based Invocation Metrics” by Gábor Antal, Zoltán Tóth, Péter Hegedűs, and Rudolf Ferenc (Department of Software Engineering) has been published by MDPI.
The article is concerned with improving the bug prediction of JavaScript applications by introducing a new, function level prediction model. Instead of just relying on static code analysis, the team used hybrid code metrics, thereby improving the performance of machine learning models by 2-10%.
The article is available for reading on MDPI’s website.
Page last modified: January 18, 2021