Home > Research > Publications & Outputs > Comparing the performance of fault prediction m...

Research

Associated organisational units

Links

Text available via DOI:

View graph of relations

Comparing the performance of fault prediction models which report multiple performance measures: Recomputing the confusion matrix

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Comparing the performance of fault prediction models which report multiple performance measures: Recomputing the confusion matrix. / Bowes, D.; Hall, T.; Gray, D.
PROMISE '12 Proceedings of the 8th International Conference on Predictive Models in Software Engineering. ACM, 2012. p. 109-118.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Bowes, D, Hall, T & Gray, D 2012, Comparing the performance of fault prediction models which report multiple performance measures: Recomputing the confusion matrix. in PROMISE '12 Proceedings of the 8th International Conference on Predictive Models in Software Engineering. ACM, pp. 109-118. https://doi.org/10.1145/2365324.2365338

APA

Bowes, D., Hall, T., & Gray, D. (2012). Comparing the performance of fault prediction models which report multiple performance measures: Recomputing the confusion matrix. In PROMISE '12 Proceedings of the 8th International Conference on Predictive Models in Software Engineering (pp. 109-118). ACM. https://doi.org/10.1145/2365324.2365338

Vancouver

Bowes D, Hall T, Gray D. Comparing the performance of fault prediction models which report multiple performance measures: Recomputing the confusion matrix. In PROMISE '12 Proceedings of the 8th International Conference on Predictive Models in Software Engineering. ACM. 2012. p. 109-118 doi: 10.1145/2365324.2365338

Author

Bowes, D. ; Hall, T. ; Gray, D. / Comparing the performance of fault prediction models which report multiple performance measures : Recomputing the confusion matrix. PROMISE '12 Proceedings of the 8th International Conference on Predictive Models in Software Engineering. ACM, 2012. pp. 109-118

Bibtex

@inproceedings{b6c72ba34f004ed993daed0d3758db93,
title = "Comparing the performance of fault prediction models which report multiple performance measures: Recomputing the confusion matrix",
abstract = "There are many hundreds of fault prediction models published in the literature. The predictive performance of these models is often reported using a variety of different measures. Most performance measures are not directly comparable. This lack of comparability means that it is often difficult to evaluate the performance of one model against another. Our aim is to present an approach that allows other researchers and practitioners to transform many performance measures of categorical studies back into a confusion matrix. Once performance is expressed in a confusion matrix alternative preferred performance measures can then be derived. Our approach has enabled us to compare the performance of 600 models published in 42 studies. We demonstrate the application of our approach on several case studies, and discuss the advantages and implications of doing this.",
author = "D. Bowes and T. Hall and D. Gray",
year = "2012",
doi = "10.1145/2365324.2365338",
language = "English",
isbn = "9781450312417",
pages = "109--118",
booktitle = "PROMISE '12 Proceedings of the 8th International Conference on Predictive Models in Software Engineering",
publisher = "ACM",

}

RIS

TY - GEN

T1 - Comparing the performance of fault prediction models which report multiple performance measures

T2 - Recomputing the confusion matrix

AU - Bowes, D.

AU - Hall, T.

AU - Gray, D.

PY - 2012

Y1 - 2012

N2 - There are many hundreds of fault prediction models published in the literature. The predictive performance of these models is often reported using a variety of different measures. Most performance measures are not directly comparable. This lack of comparability means that it is often difficult to evaluate the performance of one model against another. Our aim is to present an approach that allows other researchers and practitioners to transform many performance measures of categorical studies back into a confusion matrix. Once performance is expressed in a confusion matrix alternative preferred performance measures can then be derived. Our approach has enabled us to compare the performance of 600 models published in 42 studies. We demonstrate the application of our approach on several case studies, and discuss the advantages and implications of doing this.

AB - There are many hundreds of fault prediction models published in the literature. The predictive performance of these models is often reported using a variety of different measures. Most performance measures are not directly comparable. This lack of comparability means that it is often difficult to evaluate the performance of one model against another. Our aim is to present an approach that allows other researchers and practitioners to transform many performance measures of categorical studies back into a confusion matrix. Once performance is expressed in a confusion matrix alternative preferred performance measures can then be derived. Our approach has enabled us to compare the performance of 600 models published in 42 studies. We demonstrate the application of our approach on several case studies, and discuss the advantages and implications of doing this.

U2 - 10.1145/2365324.2365338

DO - 10.1145/2365324.2365338

M3 - Conference contribution/Paper

SN - 9781450312417

SP - 109

EP - 118

BT - PROMISE '12 Proceedings of the 8th International Conference on Predictive Models in Software Engineering

PB - ACM

ER -