A Framework for Defect Prediction in Specific Software Project Contexts

Wahyudin, Dindin; Ramler, Rudolf; Biffl, Stefan

doi:10.1007/978-3-642-22386-0_20

Cited by 11 publications

(9 citation statements)

References 21 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 Q2: Does training data from the same project always lead to better prediction results than training data from other projects? It is a common tendency to suppose that training data in the same project may leads to better prediction results than training data from other projects since different releases in a same project usually share similar contexts, e.g., the process, developers, and organization (Koru and Liu 2005;Wahyudin et al 2008). However, there is little empirical evidence to support this assumption directly.…”

Section: Introductionmentioning

confidence: 88%

“…They argued that there is significant difference between data sets, using a C4.5 decision tree, they successfully recognized which project a class belongs to with Accuracy greater than 90%. What's more, Wahyudin et al (2008) argued that prediction models learned from one project are usually not applicable for other projects because of the unique context for each project. Different data characteristics, in addition to different contexts of projects (e.g., process, developers, programming language) make cross-project defect prediction a big challenge.…”

Section: Cross-project/cross-company Defect Predictionmentioning

confidence: 98%

“…In the past decade, various defect prediction models have been proposed and machine learning techniques have been more and more popular in constructing defect predictors (Menzies et al 2007b;Ohlsson and Alberg 1996;Nagappan and Ball 2005;Nagappan et al 2006;Ostrand et al 2005;Catal and Diri 2009;Hassan and Holt 2005;Wahyudin et al 2008;Carvalho et al 2010;D'Ambros et al 2010;Jureczko and Spinellis 2010). However, most prediction models reported are intra-project applicable, i.e., learning from data of historical releases and then applying to the upcoming release in the same project.…”

Section: Defect Predictionmentioning

confidence: 98%

See 2 more Smart Citations

An investigation on the feasibility of cross-project defect prediction

et al. 2011

View full text Add to dashboard Cite

Software defect prediction helps to optimize testing resources allocation by identifying defect-prone modules prior to testing. Most existing models build their prediction capability based on a set of historical data, presumably from the same or similar project settings as those under prediction. However, such historical data is not always available in practice. One potential way of predicting defects in projects without historical data is to learn predictors from data of other projects. This paper investigates defect predictions in the cross-project context focusing on the selection of training data. We conduct three large-scale experiments on 34 data sets obtained from 10 open source projects. Major conclusions from our experiments include: (1) in the best cases, training data from other projects can provide better prediction results than training data from the same project; (2) the prediction results obtained using Z. He ( ) · training data from other projects meet our criteria for acceptance on the average level, defects in 18 out of 34 cases were predicted at a Recall greater than 70% and a Precision greater than 50%; (3) results of cross-project defect predictions are related with the distributional characteristics of data sets which are valuable for training data selection. We further propose an approach to automatically select suitable training data for projects without historical data. Prediction results provided by the training data selected by using our approach are comparable with those provided by training data from the same project.

show abstract

Section: Introductionmentioning

confidence: 88%

Section: Cross-project/cross-company Defect Predictionmentioning

confidence: 98%

Section: Defect Predictionmentioning

confidence: 98%

See 1 more Smart Citation

An investigation on the feasibility of cross-project defect prediction

et al. 2011

View full text Add to dashboard Cite

show abstract

“…For instance, the authors in [SP17] cross-checked other results but included no quality assessment question list.…”

Section: Selected Studiesmentioning

confidence: 99%

Quality assessment of systematic reviews in software engineering

Zhou

Zhang

Huang

et al. 2015

Proceedings of the 19th International Conference on Evaluation and Assessment in Software Engineering

View full text Add to dashboard Cite

Context:The quality of an Systematic Literature Review (SLR) is as good as the quality of the reviewed papers. Hence, it is vital to rigorously assess the papers included in an SLR. There has been no tertiary study aimed at reporting the state of the practice of quality assessment used in SLRs in Software Engineering (SE). Objective: We aimed to study the practices of quality assessment of the papers included in SLRs in SE. Method: We conducted a tertiary study of the SLRs that have performed quality assessment of the reviewed papers. Results: We identified and analyzed different aspects of the quality assessment of the papers included in 127 SLRs. Conclusion: Researchers use a variety of strategies for quality assessment of the papers reviewed, but report little about the justification for the used criteria. The focus is creditability but not relevance aspect of the papers. Appropriate guidelines are required for devising quality assessment strategies.

show abstract

“…Ref. [53] presented a framework for conducting software defect prediction as aid for the practitioner project managers and provided a guide to the body of existing studies on defect prediction.…”

Section: Related Workmentioning

confidence: 99%

Extracting software static defect models using data mining

Yousef

2015

Ain Shams Engineering Journal

View full text Add to dashboard Cite

Large software projects are subject to quality risks of having defective modules that will cause failures during the software execution. Several software repositories contain source code of large projects that are composed of many modules. These software repositories include data for the software metrics of these modules and the defective state of each module. In this paper, a data mining approach is used to show the attributes that predict the defective state of software modules. Software solution architecture is proposed to convert the extracted knowledge into data mining models that can be integrated with the current software project metrics and bugs data in order to enhance the prediction. The results show better prediction capabilities when all the algorithms are combined using weighted votes. When only one individual algorithm is used, Naı¨ve Bayes algorithm has the best results, then the Neural Network and the Decision Trees algorithms.Ó 2014 Production and hosting by Elsevier B.V. on behalf of Ain Shams University.

show abstract

A Framework for Defect Prediction in Specific Software Project Contexts

Cited by 11 publications

References 21 publications

An investigation on the feasibility of cross-project defect prediction

An investigation on the feasibility of cross-project defect prediction

Quality assessment of systematic reviews in software engineering

Extracting software static defect models using data mining

Contact Info

Product

Resources

About