Investigating Performance of SVM Based Classifier for Software Reusability Prediction
The re-usability is the quality of a piece of software, that enables it to be used again, be it partial, modified or complete. In this study Support Vector Machines (SVM) based classification approach is evaluated for Re-usability Prediction of Function based Software systems. As deduced from the results it is clear that Average Correct Rate or the Accuracy of the proposed system is 87.409% and the best Classification Accuracy percentage is 88.89%, which is satisfactory enough for the prediction of the function based reusable modules from the existing reservoir of software components. The proposed system can be used for identification and later can be extracted and saved in the reuse repository for its reuse.