Heterogeneous Defect Prediction via Exploiting Correlation Subspace

Abstract

Abstract-Software defect prediction generally builds models from intra-project data. Lack of training data at the early stage of software testing limits the efficiency of prediction in practice. Thereby researchers proposed cross-project defect prediction using the data from other projects. Most previous efforts assumed the cross-project defect data have the same metrics set which means the metrics used and size of metrics set are same in the data of projects. However, in real scenarios, this assumption may not hold. In addition, software defect datasets have the class imbalance problem increasing the difficulty for the learner to predict defects. In this paper, we advance canonical correlation analysis for deriving a joint feature space for associating crossproject data and propose a novel support vector machine algorithm which incorporates the correlation transfer information into classifier design for cross-project prediction. Moreover, we take different misclassification costs into consideration to make the classification inclining to classify a module as a defective one, alleviating the impact of imbalanced data. Experiments on public heterogeneous datasets from different projects show that our method is more effective, compared to state-of-the-art methods.

Heterogeneous fault prediction with cost‐sensitive domain adaptation

“…To be fair, we choose LR classifier for all compared methods except for CCT‐SVM, which uses the default SVM classifier . Comparison of CLSUP and CCT‐SVM using the SVM classifier will be reported in Section 4.5.4.…”

“…Recently, heterogeneous fault prediction (HFP) models are presented to predict faults across projects with heterogeneous metric sets, ie, source and target projects have different metric sets. For example, Jing et al presented a transfer CCA (canonical correlation analysis)+ method by using unified metric representation (UMR) and CCA‐based transfer learning technique for HFP.…”

“…Although existing HFP methods have achieved promising results, the following issues still have not been well studied. (1)Mixed project data problem : In the early phases of software testing, projects may have only a small amount of historical defect data (training target data).…”

Combing Data Filter and Data Sampling for Cross-Company Defect Prediction: An Empricial Study

“…The second mainstream way is to design effective defect predictor based on transfer learning techniques (e.g., [7,10,15,16,17,18,19]). For instance, Ma et al [15] proposed Transfer Naï ve Bayes (TNB) model.…”

“…Another challenge in CCDP is that the set of metrics between the source company data and target company data is usually heterogeneous. Jing et al [7] and Chen et al [19] proposed the effective solutions for heterogeneous cross-company defect prediction.…”