Early Outcome Prediction of Software Projects using Software Defects and Machine Learning

  • Michael Thomas Shrove Millennium Corporation
  • Emil Jovanov University of Alabama Huntsville
Keywords: machine learning, Software Quality Management, software outcome prediction, defect trend analysis, defects, svm, support vector machine


The goal of this research is to help software stakeholders predict early in the software project when or if the project is at risk of failure. If the decision makers can get an early notification of the outcome, they can make better choices on what they need to do to make the project successful. In this paper, we explore using the trend of defect totals as a function of the relative completion of the project. We collected the data from a software company who had multiple software projects that had a defined and consistent process and metric collection methods. We show how we used the defects totals from this data as features to a Support Vector Machine (SVM) to classify the project as successful or unsuccessful early in the project’s lifecycle. We present our technique and methodologies for developing the inputs for the proposed model and the results of testing. Further, we discuss the prediction model and the analysis of an SVM model. We then evaluate the labels from the company’s dataset to our prediction model and show that it demonstrates a prediction accuracy of 88.7% in a set of 13 projects.

Author Biographies

Michael Thomas Shrove, Millennium Corporation

Tommy Shrove is a Chief Software Architect (CSA) at Millennium Corporation. He received his Bachelor of Science in Computer Engineering and his Master of Science in Software Engineering from the University of Alabama in Huntsville (UAH). He is currently pursuing his Ph.D. in Computer Engineering from UAH specializing in DevOps, Machine Learning, and Artificial Intelligence (AI). Tommy has been managing large software teams for the past 12 years. He is currently at Millennium Corporation as the CSA where he works with engineers, designers, and the executive staff to help guide, brand, design, and manage the next-generation products and technology for the company by using custom innovation ideas and processes to maximize quality and efficiency. Mr. Shrove also has multiple ethical hacking certifications including ISC(2) Certified Information Systems Security Professional (CISSP), EC-Council Certified Ethical Hacker (CEH), Certified Penetration Tester (CPT). He has over 9 publications in the area of software engineering.

Emil Jovanov, University of Alabama Huntsville

Dr. Emil Jovanov is an Associate Professor in the Electrical and Computer Engineering
Department at the University of Alabama in Huntsville (UAH). He received his PhD in
Computer Engineering from the University of Belgrade in 1993 and he has been teaching at
UAH since 1998. His research interests include Wearable health monitoring, IoT (Internet
of Things), wireless and sensor networks, ubiquitous and mobile computing, and
biomedical signal processing. Dr. Jovanov has more than 30 years of experience in the
design of application specific hardware and software systems. Dr. Jovanov is recognized as
the originator of the concept of wireless body area networks for health monitoring and one
of the leaders in the field of wearable health monitoring. Dr. Jovanov is a Senior Member of
IEEE, and serves in IEEE EMBS Technical Committee on Wearable Biomedical Sensors and
Systems. He is a member of the Conference Editorial Board and Theme 7 Editor (Biomedical
Sensors and Wearable Systems) of IEEE Engineering in Medicine and Biology Society,
Associate Editor of the IEEE Transactions on Information Technology in Biomedicine and
IEEE Transactions on Biomedical Circuits and Systems, and Editorial Board member of
Applied Psychophysiology and Biofeedback. Dr. Jovanov was the Guest Editor of two special
issues of IEEE Transactions on Information Technology in Biomedicine: “Body Sensor
Networks: From Theory to Emerging Applications” (2009) and “M-Health: Beyond Seamless
Mobility and Global Wireless Health-Care Connectivity” (2004). Dr. Jovanov received 2017
IEEE Outstanding Educator Award, 2014 Innovator of the Year Award, and 2009
Outstanding Paper Award of IEEE Transactions of Information Technology in Biomedicine.
He published more than 200 papers, 16 book chapters, and 6 U.S. patents.