Software Bug Prediction Analysis Using Various Machine Learning Approaches

Abstract

Throughout software development and management systems, software Bug Prediction (SBP) is a major issue concerning overall software quality. Predicting the computer problems of previous stages increases performance, productivity and reduces costs more reliably. In fact, in advance forecasting can force us to take adequate precautionary measures to prevent bugs. Nonetheless, creating a practical framework of bug forecasting is a difficult task and various approaches are suggested in literature. This article presents few models of machine learning prediction software. The assessment process demonstrated that   algorithms can be used for  high precision. In addition, the proposed prediction model is compared to other approaches by using a comparison measure. The results showed a better performance  over other  strategy.