Identifying recurring association rules in software defect prediction

Takashi Watanabe, Akito Monden, Yasutaka Kamei, Shuji Morisaki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Association rule mining discovers patterns of co-occurrences of attributes as association rules in a data set. The derived association rules are expected to be recurrent, that is, the patterns recur in future in other data sets. This paper defines the recurrence of a rule, and aims to find a criteria to distinguish between high recurrent rules and low recurrent ones using a data set for software defect prediction. An experiment with the Eclipse Mylyn defect data set showed that rules of lower than 30 transactions showed low recurrence. We also found that the lower bound of transactions to select high recurrence rules is dependent on the required precision of defect prediction.

Original languageEnglish
Title of host publication2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509008063
DOIs
Publication statusPublished - Aug 23 2016
Event15th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2016 - Okayama, Japan
Duration: Jun 26 2016Jun 29 2016

Other

Other15th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2016
CountryJapan
CityOkayama
Period6/26/166/29/16

Fingerprint

Association rules
Association Rules
Defects
Recurrence
Software
Prediction
Transactions
Association Rule Mining
Attribute
Lower bound
Dependent
Experiments
Experiment

Keywords

  • association rule mining
  • data mining
  • defect prediction
  • empirical study
  • software quality

ASJC Scopus subject areas

  • Computer Science(all)
  • Energy Engineering and Power Technology
  • Control and Optimization

Cite this

Watanabe, T., Monden, A., Kamei, Y., & Morisaki, S. (2016). Identifying recurring association rules in software defect prediction. In 2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings [7550867] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIS.2016.7550867

Identifying recurring association rules in software defect prediction. / Watanabe, Takashi; Monden, Akito; Kamei, Yasutaka; Morisaki, Shuji.

2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. 7550867.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Watanabe, T, Monden, A, Kamei, Y & Morisaki, S 2016, Identifying recurring association rules in software defect prediction. in 2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings., 7550867, Institute of Electrical and Electronics Engineers Inc., 15th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2016, Okayama, Japan, 6/26/16. https://doi.org/10.1109/ICIS.2016.7550867
Watanabe T, Monden A, Kamei Y, Morisaki S. Identifying recurring association rules in software defect prediction. In 2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. 7550867 https://doi.org/10.1109/ICIS.2016.7550867
Watanabe, Takashi ; Monden, Akito ; Kamei, Yasutaka ; Morisaki, Shuji. / Identifying recurring association rules in software defect prediction. 2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016.
@inproceedings{2d4ed30daa9640449b5841c5d684f6ef,
title = "Identifying recurring association rules in software defect prediction",
abstract = "Association rule mining discovers patterns of co-occurrences of attributes as association rules in a data set. The derived association rules are expected to be recurrent, that is, the patterns recur in future in other data sets. This paper defines the recurrence of a rule, and aims to find a criteria to distinguish between high recurrent rules and low recurrent ones using a data set for software defect prediction. An experiment with the Eclipse Mylyn defect data set showed that rules of lower than 30 transactions showed low recurrence. We also found that the lower bound of transactions to select high recurrence rules is dependent on the required precision of defect prediction.",
keywords = "association rule mining, data mining, defect prediction, empirical study, software quality",
author = "Takashi Watanabe and Akito Monden and Yasutaka Kamei and Shuji Morisaki",
year = "2016",
month = "8",
day = "23",
doi = "10.1109/ICIS.2016.7550867",
language = "English",
booktitle = "2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Identifying recurring association rules in software defect prediction

AU - Watanabe, Takashi

AU - Monden, Akito

AU - Kamei, Yasutaka

AU - Morisaki, Shuji

PY - 2016/8/23

Y1 - 2016/8/23

N2 - Association rule mining discovers patterns of co-occurrences of attributes as association rules in a data set. The derived association rules are expected to be recurrent, that is, the patterns recur in future in other data sets. This paper defines the recurrence of a rule, and aims to find a criteria to distinguish between high recurrent rules and low recurrent ones using a data set for software defect prediction. An experiment with the Eclipse Mylyn defect data set showed that rules of lower than 30 transactions showed low recurrence. We also found that the lower bound of transactions to select high recurrence rules is dependent on the required precision of defect prediction.

AB - Association rule mining discovers patterns of co-occurrences of attributes as association rules in a data set. The derived association rules are expected to be recurrent, that is, the patterns recur in future in other data sets. This paper defines the recurrence of a rule, and aims to find a criteria to distinguish between high recurrent rules and low recurrent ones using a data set for software defect prediction. An experiment with the Eclipse Mylyn defect data set showed that rules of lower than 30 transactions showed low recurrence. We also found that the lower bound of transactions to select high recurrence rules is dependent on the required precision of defect prediction.

KW - association rule mining

KW - data mining

KW - defect prediction

KW - empirical study

KW - software quality

UR - http://www.scopus.com/inward/record.url?scp=84987941394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987941394&partnerID=8YFLogxK

U2 - 10.1109/ICIS.2016.7550867

DO - 10.1109/ICIS.2016.7550867

M3 - Conference contribution

AN - SCOPUS:84987941394

BT - 2016 IEEE/ACIS 15th International Conference on Computer and Information Science, ICIS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -