Automated Change Request Triage Using Alpha Frequency Matrix

Abstract

Software changes are inevitable in large and long lived projects. Successful applications require proper handling and assignment of change requests (CRs). In large projects, a number of CRs are generated daily. These CRs should be resolved timely. We present an automated approach to assign CRs to appropriate developers. We use Alphabet Frequency Matrix (AFM) to classify CRs into developer classes. We apply machine learning techniques on the AFM data sets for classification. We find that AFM can be used to achieve an average accuracy from 27% to 53% with precision 25% to 55% and recall 28% to 56%.