Software reuse analytics using integrated random forest and gradient boosting machine learning algorithm. (27th October 2020)

• Record Type: Journal Article
• Authors: Sandhu, Amandeep Kaur; Batth, Ranbir Singh
• Other Names: Bishop Judith guestEditor.; Cooper Kendra M.L. guestEditor.; Kim Moonzoo guestEditor.; Koziolek Heiko guestEditor.
• Is Part Of: Software, practice & experience. Volume 51:Number 4(2021)
• Page Start: 735
• Page End: 747
• Publication Date: 2020-10-27
• Subjects: AdaBoostM1 -- confusion matrix -- DecisionStump -- gradient boosting machine -- J48 -- JRip -- LMT -- LogitBoost -- one R -- part -- random forest -- software metrics -- software reuse; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2921
• Languages: English
• ISSNs: 0038-0644

Abstract

Abstract: The term Cleaner Production (CP) for Production Companies is contemplated as influential to get sustainable production. CP mainly deals with three R's that is, reuse, reduce, and recycle. For software enterprise, the software reuse plays a pivotal role. Software reuse is a process of producing new products or software from the existing software by updating it. To extract useful information from the existing software data mining comes into light. The algorithms used for software reuse face issues related to maintenance cost, accuracy, and performance. Also, the currently used algorithm does not give accurate results on whether the component of software can be reused. Machine Learning gives the best results to predicate if the given software component is reusable or not. This paper introduces an integrated Random Forest and Gradient Boosting Machine Learning Algorithm (RFGBM) which test the reusability of the given software code considering the object‐oriented parameters such as cohesion, coupling, cyclomatic complexity, bugs, number of children, and depth inheritance tree. Further, the proposed algorithm is compared with J48, AdaBoostM1, LogitBoost, Part, One R, LMT, JRip, DecisionStump algorithms. Performance metrices like accuracy, error rate, Relative Absolute Error, and Mean Absolute Error are improved using RFGBM. This algorithm also utilizes data preprocessing with the help of an unsupervised filter to remove the missing value for efficiency improvement. Proposed algorithm outperforms existing in term of performance parameters.