Treffer: Enhancing Refactoring Prediction at the Method-Level Using Stacking and Boosting Models.

Refactoring software code is crucial for developers since it enhances code maintainability and decreases technical complexity. The existing manual approach to refactoring demonstrates restricted scalability because of its requirement for substantial human intervention and big training information. A method-level refactoring prediction technique based on meta-learning uses classifier stacking and boosting and Lion Optimization Algorithm (LOA) for feature selection. The evaluation of the proposed model used four Java open source projects namely JUnit, McMMO, MapDB, and ANTLR4 showing exceptional predictive results. The technique successfully decreased training data necessities by 30% yet generated better prediction results by 10-15% above typical models to deliver 100% accuracy and F1 scores on DTS3 and DTS4 datasets. The system decreased incorrect refactoring alert counts by 40% which lowered the amount of needed developer examination. [ABSTRACT FROM AUTHOR]

Copyright of Jurnal Ilmiah Teknik Elektro Komputer dan Informatika is the property of Jurnal Ilmiah Teknik Elektro Komputer dan Informatika and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)