A Hyper-parameter Tuning based Novel Model for Prediction of Software Maintainability

Software maintainability is regarded as one of the most important characteristics any software system. In today's digital world, expanding significance maintenance motivating development efficient prediction (SMP) models using statistical and machine learning methods. This study proposes a hyper-parameter optimizable Maintainability Prediction (HPOSMP) model hybridized approach data balancing optimization Machine Learning (ML) datasets. The training dataset has been created with object-oriented namely UIMS QUES. To balance dataset, Synthetic Minority Oversampling Technique (SMOTE) technology adopted. Further, Decision Tree, Gaussian Naïve Bayes, K-Nearest neighbour, Logistic Regression, Support Vector are adopted Statistical Regression Techniques for dataset. Results demonstrate that proposed HPOSMP gives better performance compared to base SMP models.