There is always a desire for defect-free software in order to maintain software quality for customer satisfaction and to save testing expenses. As a result, we examined various known ML techniques and optimized ML techniques on a freely available data set. The purpose of the research was to improve the model performance in terms of accuracy and precision of the dataset compared to previous research. As previous investigations show, the accuracy can be further improved. For this purpose, we employed K-means clustering for the categorization of class labels. Further, we applied classification models to selected features. Particle Swarm Optimization is utilized to optimize ML models. We evaluated the performance of models through precision, accuracy, recall, f-measure, performance error metrics, and a confusion matrix. The results indicate that all the ML and optimized ML models achieve the maximum results; however, the SVM and optimized SVM models outperformed with the highest achieved accuracy, 99% and 99.80%, respectively. The accuracy of NB, Optimized NB, RF, Optimized RF and ensemble approaches are 93.90%, 93.80%, 98.70%, 99.50%, 98.80% and 97.60, respectively. In this way, we achieve maximum accuracy compared to previous studies, which was our goal.

Feature selection is the process of identifying the most relevant features from the given data having a large feature space. Microarray datasets are comprised of high‐quality features and very few samples of data. Feature selection is performed on such datasets to identify the optimal feature subset. The major goal of feature selection is to improve the accuracy by identifying a minimal feature subset. For this purpose, the proposed research focused on analyzing and identifying effective feature selection algorithms. A novel framework is proposed which utilizes different feature selection methods from filters, wrappers, and embedded algorithms. Furthermore, classification is then performed on selected features to classify the data using a support vector machine (SVM) classifier. Two publically available benchmark datasets are used, i.e., the Microarray dataset and the Cleveland Heart Disease dataset, for experimentation and analysis, and they are archived from the UCI data repository. The performance of SVM is analyzed using accuracy, sensitivity, specificity, and f‐measure. The accuracy of 94.45% and 91% is achieved on each dataset, respectively.