The Impact of Software Fault Prediction in Real-World Application: An Automated Approach for Software Engineering Md. Razu Ahmed Department of Software Engineering Daffodil International University Dhaka-1207, Bangladesh Cell: +8801787844301 razu35-1072@diu.edu.bd Md. Fahad Bin Zamal Department of Software Engineering Daffodil International University Dhaka-1207, Bangladesh fahad.swe@diu.edu.bd Md. Asraf Ali Department of Software Engineering Daffodil International University Dhaka-1207, Bangladesh asraf.swe@diu.edu.bd F.M. Javed Mehedi Shamrat Department of Software Engineering Daffodil International University Dhaka-1207, Bangladesh javedmehedicom@gmail.com Nasim Ahmed School of Natural and Computational Sciences, Massey University Albany 0632, Auckland, New Zealand nasim751@yahoo.com ABSTRACT Software fault prediction and proneness has long been considered as a critical issue for the tech industry and software professionals. In the traditional techniques, it requires previous experience of faults or a faulty module while detecting the software faults inside an application. An automated software fault recovery models enable the software to significantly predict and recover software faults using machine learning techniques. Such ability of the feature makes the software to run more effectively and reduce the faults, time and cost. In this paper, we proposed a software defect predictive development models using machine learning techniques that can enable the software to continue its projected task. Moreover, we used different prominent evaluation benchmark to evaluate the model’s performance such as ten-fold cross- validation techniques, precision, recall, specificity, f 1 measure, and accuracy. This study reports a significant classification performance of 98-100% using SVM on three defect datasets in terms of f1 measure. However, software practitioners and researchers can attain independent understanding from this study while selecting automated task for their intended application. CCS Concepts Computing methodologies➝ Machine learning algorithms Keywords Software engineering; Software fault; Machine learning; Defect prediction. 1. INTRODUCTION The vast area of software development and different applications makes it challenging for software developers and also customers to observe, maintains and manage software applications. Moreover, the fourth industrial revolution employs artificial intelligence by software industry is one of the promising sectors of modern times that observes a constant transformation in its practices because of the automating large quantities of software technologies [1]. The size and complexity of current software is increasing day by day. As a result, software engineers are struggling continuously with faults from the beginning of the development phase. The classification of the software faults is important in real-time, otherwise, the effort and cost of finding defects hiding in an application are also rising fast. This inspires the development of automated fault prediction models for software fault prediction that can forecast the software defects. If software defects are identified before the release of software that can help the developer to allocate and fix those defect modules easily. Software fault prediction through machine learning techniques are being the most prominent use case among the researchers and the software community [2]. State of the art machine learning algorithms have been applied to find the defect modules from the software applications for research and make effective solutions for consumers [3]. In this study, we have used the six most popular of the machine learning classifiers which are suggested in the most recent systematic literature study [4]. All selected classification techniques are applied over different real application datasets related to the software fault prediction of the applications. However, we have to consider particular features in terms of their quality of data but that cannot be validated in terms of correctness. Therefore, the state of the art [5] machine learning approaches have been applied to the fault datasets to enhance the prediction by reducing unnecessary features through several feature selection techniques and imbalance to balancing data methods. Many of the studies examined fault recovery methods into software with their focus on combining the automated recovery model inside the application [6][7][8]. The goal of this study is examined with six classifiers' performance and recommends an automated approach to solve software faults inside a software. We used three data sets (i.e. JM1, CM1, PC1) from PROMISE Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Permissions@acm.org. ICCDE '20, January 4–6, 2020, Sanya, China © 2020 Association for Computing Machinery. ACM ISBN 978-1-4503-7673-0/20/01…$15.00 https://doi.org/10.1145/3379247.3379278 247 International Conference on Computing and Data Engineering (ICCDE2020) Sanya, China