Investigating the Effect of Software Metrics Aggregation on Software Fault Prediction

Deepanshu Dixit, Sandeep Kumar

Abstract

In inter-releases software fault prediction, the data from the previous version of the software that is used for training the classifier might not always be of same granularity as that of the testing data. The same scenario may also happen in the cross project software fault prediction. So, one major issue in it can be the difference in granularity i.e. training and testing datasets may not have the metrics at the same level. Thus, there is a need to bring the metrics at the same level. In this paper, aggregation using Average Absolute Deviation (AAD) and Interquartile Range (IQR) are explored. We propose the method for aggregation of metrics from class to package level for software fault prediction and validated the approach by performing experimental analysis. We did the experimental study to analyze the performance of software fault prediction mechanism when no aggregation technique was used and when the two mentioned aggregation techniques were used. The experimental study revealed that the aggregation improved the performance and out of AAD and IQR aggregation techniques, IQR performs relatively better.

Download


Paper Citation


in Harvard Style

Dixit D. and Kumar S. (2018). Investigating the Effect of Software Metrics Aggregation on Software Fault Prediction.In Proceedings of the 13th International Conference on Software Technologies - Volume 1: ICSOFT, ISBN 978-989-758-320-9, pages 304-311. DOI: 10.5220/0006884003040311


in Bibtex Style

@conference{icsoft18,
author={Deepanshu Dixit and Sandeep Kumar},
title={Investigating the Effect of Software Metrics Aggregation on Software Fault Prediction},
booktitle={Proceedings of the 13th International Conference on Software Technologies - Volume 1: ICSOFT,},
year={2018},
pages={304-311},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006884003040311},
isbn={978-989-758-320-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Software Technologies - Volume 1: ICSOFT,
TI - Investigating the Effect of Software Metrics Aggregation on Software Fault Prediction
SN - 978-989-758-320-9
AU - Dixit D.
AU - Kumar S.
PY - 2018
SP - 304
EP - 311
DO - 10.5220/0006884003040311