Characterization and prediction of issue-related risks in software projects

© 2015 IEEE. Identifying risks relevant to a software project and planning measures to deal with them are critical to the success of the project. Current practices in risk assessment mostly rely on high-level, generic guidance or the subjective judgements of experts. In this paper, we propose a nove...

Full description

Bibliographic Details
Main Authors: Choetkiertikul, M., Dam, H., Tran, The Truyen, Ghose, A.
Format: Conference Paper
Published: 2015
Online Access:http://hdl.handle.net/20.500.11937/16791
_version_ 1848749278168612864
author Choetkiertikul, M.
Dam, H.
Tran, The Truyen
Ghose, A.
author_facet Choetkiertikul, M.
Dam, H.
Tran, The Truyen
Ghose, A.
author_sort Choetkiertikul, M.
building Curtin Institutional Repository
collection Online Access
description © 2015 IEEE. Identifying risks relevant to a software project and planning measures to deal with them are critical to the success of the project. Current practices in risk assessment mostly rely on high-level, generic guidance or the subjective judgements of experts. In this paper, we propose a novel approach to risk assessment using historical data associated with a software project. Specifically, our approach identifies patterns of past events that caused project delays, and uses this knowledge to identify risks in the current state of the project. A set of risk factors characterizing 'risky' software tasks (in the form of issues) were extracted from five open source projects: Apache, Duraspace, JBoss, Moodle, and Spring. In addition, we performed feature selection using a sparse logistic regression model to select risk factors with good discriminative power. Based on these risk factors, we built predictive models to predict if an issue will cause a project delay. Our predictive models are able to predict both the risk impact (i.e. The extend of the delay) and the likelihood of a risk occurring. The evaluation results demonstrate the effectiveness of our predictive models, achieving on average 48% - 81% precision, 23% - 90% recall, 29% - 71% F-measure, and 70% - 92% Area Under the ROC Curve. Our predictive models also have low error rates: 0.39 - 0.75 for Macro-averaged Mean Cost-Error and 0.7 - 1.2 for Macro-averaged Mean Absolute Error.
first_indexed 2025-11-14T07:18:24Z
format Conference Paper
id curtin-20.500.11937-16791
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:18:24Z
publishDate 2015
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-167912018-03-29T09:06:20Z Characterization and prediction of issue-related risks in software projects Choetkiertikul, M. Dam, H. Tran, The Truyen Ghose, A. © 2015 IEEE. Identifying risks relevant to a software project and planning measures to deal with them are critical to the success of the project. Current practices in risk assessment mostly rely on high-level, generic guidance or the subjective judgements of experts. In this paper, we propose a novel approach to risk assessment using historical data associated with a software project. Specifically, our approach identifies patterns of past events that caused project delays, and uses this knowledge to identify risks in the current state of the project. A set of risk factors characterizing 'risky' software tasks (in the form of issues) were extracted from five open source projects: Apache, Duraspace, JBoss, Moodle, and Spring. In addition, we performed feature selection using a sparse logistic regression model to select risk factors with good discriminative power. Based on these risk factors, we built predictive models to predict if an issue will cause a project delay. Our predictive models are able to predict both the risk impact (i.e. The extend of the delay) and the likelihood of a risk occurring. The evaluation results demonstrate the effectiveness of our predictive models, achieving on average 48% - 81% precision, 23% - 90% recall, 29% - 71% F-measure, and 70% - 92% Area Under the ROC Curve. Our predictive models also have low error rates: 0.39 - 0.75 for Macro-averaged Mean Cost-Error and 0.7 - 1.2 for Macro-averaged Mean Absolute Error. 2015 Conference Paper http://hdl.handle.net/20.500.11937/16791 10.1109/MSR.2015.33 restricted
spellingShingle Choetkiertikul, M.
Dam, H.
Tran, The Truyen
Ghose, A.
Characterization and prediction of issue-related risks in software projects
title Characterization and prediction of issue-related risks in software projects
title_full Characterization and prediction of issue-related risks in software projects
title_fullStr Characterization and prediction of issue-related risks in software projects
title_full_unstemmed Characterization and prediction of issue-related risks in software projects
title_short Characterization and prediction of issue-related risks in software projects
title_sort characterization and prediction of issue-related risks in software projects
url http://hdl.handle.net/20.500.11937/16791