Abstract
This study examines temporal patterns of software systems defects using the Autoregressive Integrated Moving Average (ARIMA) approach. Defect reports from ten software application projects are analyzed; five of these projects are open source and five are closed source from two software vendors. Across all sampled projects, the ARIMA time series modeling technique provides accurate estimates of reported defects during software maintenance, with organizationally dependent parameterization. In contrast to causal models that require extraction of source-code level metrics, this approach is based on readily available defect report data and is less computation intensive. This approach can be used to improve software maintenance and evolution resource allocation decisions and to identify outlier projects—that is, to provide evidence of unexpected defect reporting patterns that may indicate troubled projects.
Highlights
Today’s software systems are fragile [1], when new software releases are deployed [2]
Causal and learning models are both computationally complex and require significant investments in project data collection. In response to these challenges, the goal of this study is to provide a method of predicting patterns in software defects that is accurate without the cost and complexity of more traditional predictive methods
A *NIX/*BSD system running Netatalk is capable of serving many Macintosh clients simultaneously as an AppleShare file server (AFP), AppleTalk router, *NIX/*BSD print server, and for accessing AppleTalk printers
Summary
Today’s software systems are fragile [1], when new software releases are deployed [2]. Software maintenance managers must ensure product quality and required service levels, while simultaneously minimizing costs associated with defect resolution and penalties for non-performance [10,11]. Faced with this challenge, formal predictive models are not common in resource planning; instead maintenance planning methods in practice continue to be largely ad hoc [12], with recent personal experience weighing heavily on practitioner predictions of change requests and staffing needs [10,12]. Maintenance project managers too often either overstaff (causing resources to idle and costs to increase) or understaff (causing delays in defect resolution and a decline in user satisfaction and business value)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
