Identifying recurring association rules in software defect prediction

Watanabe, Takashi; Monden, Akito; Kamei, Yasutaka; Morisaki, Shuji

doi:10.1109/icis.2016.7550867

Cited by 10 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the predictor variables are the rule's confidence and the occurrence. We choose to employ these two metrics because, in our previous study [4], we found that they were key indicators of rule prediction power. A low occurrence is acceptable, if the confidence is very high, but not if the confidence is lower.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…That said, our previous study [4] showed that setting constant lower bounds for these metrics is insufficient. For example, we can accept rules with low support if their confidence is very high, but not otherwise.…”

Section: Rule Metrics and Motivating Examplementioning

confidence: 98%

“…Association rule mining discovers relationships among variables in a given data set and represents them as association rules. In the software engineering field, it has been applied to discover rules in software defect data sets [1]- [4], such as "(max nest level > 5) and (fan-out > 5) ⇒ faulty". This rule implies that a software module is likely to contain a defect (i.e.…”

Section: Introductionmentioning

confidence: 99%

“…In regression model, the objective variable is the cross-validation prediction accuracy. And we choose the rules' confidence and occurrence as predictor variables, since these are regarded as important factors in their predictive power [4].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Cross-Validation-Based Association Rule Prioritization Metric for Software Defect Characterization

Watanabe

Monden

Yücel

et al. 2018

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

Association rule mining discovers relationships among variables in a data set, representing them as rules. These are expected to often have predictive abilities, that is, to be able to predict future events, but commonly used rule interestingness measures, such as support and confidence, do not directly assess their predictive power. This paper proposes a cross-validation -based metric that quantifies the predictive power of such rules for characterizing software defects. The results of evaluation this metric experimentally using four open-source data sets (Mylyn, NetBeans, Apache Ant and jEdit) show that it can improve rule prioritization performance over conventional metrics (support, confidence and odds ratio) by 72.8% for Mylyn, 15.0% for NetBeans, 10.5% for Apache Ant and 0 for jEdit in terms of SumNormPre(100) precision criterion. This suggests that the proposed metric can provide better rule prioritization performance than conventional metrics and can at least provide similar performance even in the worst case.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Rule Metrics and Motivating Examplementioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cross-Validation-Based Association Rule Prioritization Metric for Software Defect Characterization

Watanabe

Monden

Yücel

et al. 2018

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The parameter length is a marker of standard's unpredictability (bigger length shows progressively complex rules) which is equivalent to the quantity of things in precursor. [12] …… (6) Equation (2 )is the fitness function used in Bacterial colony optimization where w1 = w2 and w1 + w2 =1 [4].…”

Section: ………(5)mentioning

confidence: 99%

Extraction of Association Rule Mining using Apriori algorithm with Wolf Search Optimisation in R Programming

2019

ijrte

View full text Add to dashboard Cite

Association rules mining (ARM) is a standout amongst the most essential Data Mining Systems. Find attribute patterns as a binding rule in a data set. The discovery of these suggestion rules would result in a mutual method. Firstly, regular elements are produced and therefore the association rules are extracted. In the literature, different algorithms inspired by nature have been proposed as BCO, ACO, PSO, etc. to find interesting association rules. This article presents the performance of the ARM hybrid approach with the optimization of wolf research based on two different fitness functions. The goal is to discover the best promising rules in the data set, avoiding optimal local solutions. The implementation is done in numerical data that require data discretization as a preliminary phase and therefore the application of ARM with optimization to generate the best rules.

show abstract

Software defect prediction based on correlation weighted class association rule mining

Shao

Liu

Wang

et al. 2020

Knowledge-Based Systems

View full text Add to dashboard Cite

Identifying recurring association rules in software defect prediction

Cited by 10 publications

References 12 publications

Cross-Validation-Based Association Rule Prioritization Metric for Software Defect Characterization

Cross-Validation-Based Association Rule Prioritization Metric for Software Defect Characterization

Extraction of Association Rule Mining using Apriori algorithm with Wolf Search Optimisation in R Programming

Software defect prediction based on correlation weighted class association rule mining

Contact Info

Product

Resources

About