Bug Triage Using Data Reduction with Priority and Security

Many Open Source Software Development organizations pay quite 45 % of expense in solving bugs. Bug triaging is significant phase in procedure of bug solving. The purpose of bug triaging is to allocate coming bugs to appropriate developer. The current bug triaging methodologies are initiated on algorithms, which form classifiers from the training data sets of bug report into training, these methods are suffering from huge scale and low quality training set. Here, the training sets reduction with feature selection method Chi Square Statistic (CH) and instance selections method Iterative Case Filter (ICF) for bug triaging are suggested. Feature selection and instance selections methods are used to get better the correctness of CHI, instance selections algorithm Iterative Case Filters (ICF) are premeditated. The training sets reduction by the bug records is calculated. For training sets, 70 % words and 50 % bugs report are separated after training sets lessening. The outcome illustrates that novel and minor training data sets deliver improved correctness than unique one. The next advantage is, it provides priority according to severity of bug so that bug can be solved on the priority basis and security using AES algorithm so that no another developer can access it.