Validating the Effectiveness of Object-Oriented Metrics for Predicting Maintainability

In this study, empirically investigates the relationship of existing class level object-oriented metrics with a quality parameter i.e., maintainability. Here, different subset of Object-Oriented software metrics have been considered to provide requisite input data to design the models for predicting maintainability using Neuro-Genetic algorithm (hybrid approach of neural network and genetic algorithm). This technique is applied to estimate maintainability on two different case studies such as Quality Evaluation System (QUES) and User Interface System (UIMS). The performance parameters of this technique are evaluated based on the basis of Mean absolute error (MAE), Mean Absolute Relative Error (MARE), Root Mean Square Error (RMSE), and Standard Error of the Mean (SEM). The results reported that the identified subset metrics demonstrated an improved maintainability prediction with higher accuracy.