Detecting Outliers Using Rule-Based Modeling for Improving CBR-Based Software Quality Classification Models

摘要

Deploying a software product that is of high quality is a major concern for the project management team. Significant research has been dedicated toward developing methods for improving the quality of metrics-based software quality classification models. Several studies have shown that the accuracy of such models improves when outliers and data noise are removed from the training data set. This study presents a new approach called Rule-Based Modeling (RBM) for detecting and removing training data outliers in an effort to improve the accuracy of a Case-Based Reasoning (CBR) classification model. We chose to study CBR models because of their sensitivity to outliers in the training data set. Furthermore, we wanted to affirm the RBM technique as a viable outlier detector. We evaluate our approach by comparing the classification accuracy of CBR models built with and without removing outliers from the training data set. It is demonstrated that applying the RBM technique for eliminating outliers significantly improves the accuracy of CBR-based software quality classification models.