Cross-project defect prediction with meta-Learning

Abstract

The prediction of defects in a target project based on data from external projects is called Cross-Project Defect Prediction (CPDP). Several methods have been proposed to improve the predictive performance of CPDP models. However, there is a lack of comparison among state-of-the-art methods. Moreover, previous work has shown that the most suitable method for a project can vary according to the project being predicted. This makes the choice of which method to use difficult. We provide an extensive experimental comparison of 31 CPDP methods derived from state-of-the-art approaches, applied to 47 versions of 15 open source software projects. Four methods stood out as presenting the best performances across datasets. However, the most suitable among these methods still varies according to the project being predicted. Therefore, we propose and evaluate a meta-learning solution designed to automatically select and recommend the most suitable CPDP method for a project. Our results show that the meta-learning solution is able to learn from previous experiences and recommend suitable methods dynamically. When compared to the base methods, however, the proposed solution presented minor difference of performance. These results provide valuable knowledge about the possibilities and limitations of a meta-learning solution applied for CPDP.

complexFuzzy: A novel clustering method for selecting training instances of cross-project defect prediction

“…Despite the fact that the method yielded promising results, it does not bring any novelty with respect to the selection of training data instances. Porto et al proposed a meta-learning method to increase CPDP performance [43]. They pointed out that a CPDP method should be selected regarding the properties of the project being predicted.…”

Kosinüs Benzerliğine Dayalı Çapraz-proje Hata Tahmini

“…Yöntem umut verici sonuçlar vermesine rağmen, eğitim örneklerinin seçimiyle ilgili bir yenilik getirmemiştir. Porto ve arkadaşları [25] çapraz-proje tahmin başarısını arttırabilmek için bir meta-öğrenme yöntemi önermişlerdir. Dahası, çapraz-proje tahmin yönteminin tahmin edilen projenin özelliklerine bakarak seçilmesi gerektiğine işaret etmişlerdir.…”

Dissimilarity Space Based Multi-Source Cross-Project Defect Prediction

“…CPDP uses transferring learning methods to obtain useful information from the source domain that is similar to the distribution of the target data. This method can satisfy the same distribution hypothetical requirement between training and test data [4]. However,…”