Process Cube for Software Defect Resolution

Abstract

Online Analytical Processing (OLAP) cube is a multi-dimensional dataset used for analyzing data in a Data Warehouse (DW) for the purpose of extracting actionable intelligence. Process mining consists of analyzing event log data produced from Process Aware Information Systems (PAIS) for the purpose of discovering and improving business processes. Process cube is a concept which falls at the intersection of OLAP cube and process mining. Process cube facilitates process mining from multiple-dimensions and enables comparison of process mining results across various dimensions. We present an application of process cube to software defect resolution process to analyze and compare process data from a multi-dimensional perspective. We present a framework, a novel perspective to mine software repositories using process cube. Each cell of process cube is defined by metrics from multiple process mining perspectives like control flow, time, conformance and organizational perspective. We conduct a case-study on Google Chromium project data in which the software defect resolution process spans three software repositories: Issue Tracking System (ITS), Peer Code Review System (PCR) and Version Control System (VCS). We define process cube with 9 dimensions as issue report timestamp, priority, state, closed status, OS, component, bug type, reporter and owner. We define hierarchies along various dimensions and cluster members to handle sparsity. We apply OLAP cube operations such as slice, dice, roll-up and drill-down, and create materialized sub log for each cell. We demonstrate the solution approach by discovering process map and compare process mining results from Control Flow and Time perspective for Performance and Security issues.