Prediction of Software Bug Fixing Time Using Intuitionistic Fuzzy Similarity Measure on Bug Informative Terms

Nowadays, industries are more concerned with the timely delivery of quality software. The release of software totally depends upon the time required to fix the software bugs. The project team has to estimate the average time required to fix the bugs in accordance with the project schedule and available resources. The severity and priority of the software bug play a significant role in estimating the average time required to fix the bugs. However, the presence of multiple classes of severity and priority poses a greater challenge for the project team in terms of bug fixing time estimation. To address the aforementioned problem in this paper, an intuitionistic fuzzy similarity (IFS) measure-based bug time estimation technique is developed using the priority and severity of the software bug. The informative terms of severity and priority are used to determine the IFS measure of a new bug to multiple classes of severity and priority. The average bug fixing time for each severity and priority groups is utilized to predict the bug fixing time of a newly reported bug. The proposed bug estimation techniques provide a better MAE, RMSE, and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex> score over various software bug repositories compared to other bug fixing time estimation techniques.