Feature selection (FS) is a feasible solution for mitigating high dimensionality problem, and many FS methods have been proposed in the context of software defect prediction (SDP). Moreover, many empirical studies on the impact and effectiveness of FS methods on SDP models often lead to contradictory experimental results and inconsistent findings. These contradictions can be attributed to relative study limitations such as small datasets, limited FS search methods, and unsuitable prediction models in the respective scope of studies. It is hence critical to conduct an extensive empirical study to address these contradictions to guide researchers and buttress the scientific tenacity of experimental conclusions. In this study, we investigated the impact of 46 FS methods using Naïve Bayes and Decision Tree classifiers over 25 software defect datasets from 4 software repositories (NASA, PROMISE, ReLink, and AEEEM). The ensuing prediction models were evaluated based on accuracy and AUC values. Scott–KnottESD and the novel Double Scott–KnottESD rank statistical methods were used for statistical ranking of the studied FS methods. The experimental results showed that there is no one best FS method as their respective performances depends on the choice of classifiers, performance evaluation metrics, and dataset. However, we recommend the use of statistical-based, probability-based, and classifier-based filter feature ranking (FFR) methods, respectively, in SDP. For filter subset selection (FSS) methods, correlation-based feature selection (CFS) with metaheuristic search methods is recommended. For wrapper feature selection (WFS) methods, the IWSS-based WFS method is recommended as it outperforms the conventional SFS and LHS-based WFS methods.

Software defect prediction (SDP) is the process of predicting defects in software modules, it identifies the modules that are defective and require extensive testing. Classification algorithms that help to predict software defects play a major role in software engineering process. Some studies have depicted that the use of ensembles is often more accurate than using single classifiers. However, variations exist from studies, which posited that the efficiency of learning algorithms might vary using different performance measures. This is because most studies on SDP consider the accuracy of the model or classifier above other performance metrics. This paper evaluated the performance of single classifiers (SMO, MLP, kNN and Decision Tree) and ensembles (Bagging, Boosting, Stacking and Voting) in SDP considering major performance metrics using Analytic Network Process (ANP) multi-criteria decision method. The experiment was based on 11 performance metrics over 11 software defect datasets. Boosted SMO, Voting and Stacking Ensemble methods ranked highest with a priority level of 0.0493, 0.0493 and 0.0445 respectively. Decision tree ranked highest in single classifiers with 0.0410. These clearly show that ensemble methods can give better classification results in SDP and Boosting method gave the best result. In essence, it is valid to say that before deciding which model or classifier is better for software defect prediction, all performance metrics should be considered.Keywords— Data mining, Machine Learning,  Multi Criteria Decision Making, Software Defect Prediction

Class imbalance is a prevalent problem in machine learning which affects the prediction performance of classification algorithms. Software Defect Prediction (SDP) is no exception to this latent problem. Solutions such as data sampling and ensemble methods have been proposed to address the class imbalance problem in SDP. This study proposes a combination of Synthetic Minority Oversampling Technique (SMOTE) and homogeneous ensemble (Bagging and Boosting) methods for predicting software defects. The proposed approach was implemented using Decision Tree (DT) and Bayesian Network (BN) as base classifiers on defects datasets acquired from NASA software corpus. The experimental results showed that the proposed approach outperformed other experimental methods. High accuracy of 86.8% and area under operating receiver characteristics curve value of 0.93% achieved by the proposed technique affirmed its ability to differentiate between the defective and non-defective labels without bias.

No abstract

Nowadays, software firms are playing very important roles in economies all over the world, and majority of these firms are Small and Medium Enterprises (SMEs). The SMEs recognize that it is important to improve their development processes and activities in order to produce software with high quality and to be competitive in the software industry. However, several studies have shown that the SMEs used ad-hoc manner in their development processes and they suffer from lack of the knowledge and resources to do Software Process Improvement (SPI). In this paper, a Systematic Literature Review (SLR) is used to identify and discuss the SPI initiatives in SME software firms. The results of the systematic review showed that the majority of software process improvement initiatives in SME firms are carried out in America and Europe. Only in one Asian country, Hong Kong was the SPI initiative considered and CMM Fast-Track was the model developed. The developed model did not cover all the CMM levels, only levels 1 and 2 were considered. In conclusion, many Software Process Improvement initiatives have been proposed for SME software firms but they have shortcomings such as lack of generalizability and take a lot of time to gain the benefits/advantage of the SPI model after implementation.

Failure of software systems as a result of software testing is very much rampant as modern software systems are large and complex. Software testing which is an integral part of the software development life cycle (SDLC), consumes both human and capital resources. As such, software defect prediction (SDP) mechanisms are deployed to strengthen the software testing phase in SDLC by predicting defect prone modules or components in software systems. Machine learning models are used for developing the SDP models with great successes achieved. Moreover, some studies have highlighted that a combination of machine learning models as a form of an ensemble is better than single SDP models in terms of prediction accuracy. However, the efficiency of machine learning models can change with diverse predictive evaluation metrics. Thus, more studies are needed to establish the effectiveness of ensemble SDP models over single SDP models. This study proposes the deployment of Multi-Criteria Decision Method (MCDM) techniques to rank machine learning models. Analytic Network Process (ANP) and Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) which are types of MCDM techniques are deployed on 9 machine learning models with 11 performance evaluation metrics and 11 software defects datasets. The experimental results showed that ensemble SDP models are best appropriate SDP models as Boosted SMO and Boosted PART ranked highest for each of the MCDM techniques. Besides, the experimental results also validated the stand of not considering accuracy as the only performance evaluation metrics for SDP models. Conclusively, more performance metrics other than predictive accuracy should be considered when ranking and evaluating machine learning models. Keywords: Ensemble; Multi-Criteria Decision Method; Software Defect Prediction

No abstract

Software testing using software defect prediction aims to detect as many defects as possible in software before the software release. This plays an important role in ensuring quality and reliability. Software defect prediction can be modeled as a classification problem that classifies software modules into two classes: defective and non-defective; and classification algorithms are used for this process. This study investigated the impact of feature selection methods on classification via clustering techniques for software defect prediction. Three clustering techniques were selected; Farthest First Clusterer, K-Means and Make-Density Clusterer, and three feature selection methods: Chi-Square, Clustering Variation, and Information Gain were used on software defect datasets from NASA repository. The best software defect prediction model was farthest-first using information gain feature selection method with an accuracy of 78.69%, precision value of 0.804 and recall value of 0.788. The experimental results showed that the use of clustering techniques as a classifier gave a good predictive performance and feature selection methods further enhanced their performance. This indicates that classification via clustering techniques can give competitive results against standard classification methods with the advantage of not having to train any model using labeled dataset; as it can be used on the unlabeled datasets.Keywords: Classification, Clustering, Feature Selection, Software Defect PredictionVol. 26, No 1, June, 2019