Predictive Analytics in QA Automation:

Redefining Defect Prevention for US Enterprises

Authors

  • Gazi Touhidul Alam Master of Science in Business Analytics, Trine University, Allen Park, MI, USA. Author
  • Mohammed Majid Bakhsh Master of Science in Information Technology, Washington University of Science & Technology (WUST), Alexandria, Virginia, USA. Author
  • Nusrat Yasmin Nadia Master of Science in Information Technology, Washington University of Science & Technology (WUST), Alexandria, Virginia, USA. Author
  • S A Mohaiminul Islam Master of Science in Information Technology, Washington University of Science & Technology (WUST), Alexandria, Virginia, USA. Author

DOI:

https://doi.org/10.60087/jklst.v4.n2.005

Abstract

An essential component of contemporary software development is quality assurance (QA) automation, which guarantees program dependability, effectiveness, and user pleasure. Traditional QA techniques, on the other hand, frequently have trouble finding flaws early in the software development lifecycle, which raises expenses and delays releases. By predicting possible flaws before they appear, predictive analytics which is fueled by machine learning (ML) and artificial intelligence (AI) offers a revolutionary approach to QA automation. This study examines how predictive analytics might improve software quality and expedite testing procedures, hence redefining defect prevention for American businesses. This study uses a systematic methodology that combines machine learning-based defect prediction with real-world case studies, analyzing defect trends and evaluating the effectiveness of predictive models. The results show that enterprises leveraging predictive analytics in QA automation experience higher defect detection rates reduced testing overhead, and faster release cycles. The study identifies key machine learning models, such as Random Forests, Support Vector Machines (SVM), and Neural Networks, which have demonstrated significant accuracy in defect prediction. It also discusses the integration of predictive analytics within DevOps and CI/CD pipelines, enabling continuous monitoring and proactive defect prevention. Defect prediction skills will be significantly improved in the future by developments in Explainable AI (XAI), deep learning models, and Natural Language Processing (NLP). In addition to supporting data-driven decision-making, model transparency, and continuous learning frameworks, this article offers important advice for businesses looking to integrate predictive analytics into their QA procedures. U.S. businesses may go from reactive to proactive QA approaches by adopting predictive analytics, which will guarantee better software quality, lower expenses, and an enhanced user experience

Downloads

Download data is not yet available.

References

Alenezi, M., Alrabiah, A., & Al-Emran, M. (2019). Software defect prediction using machine learning techniques: A systematic review. Journal of Software Engineering and Applications, 12(4), 125-135.

Bergmann, M., & Zeller, A. (2018). Mining bug reports for defect prediction: Challenges and solutions. Empirical Software Engi-neering, 23(2), 553-582.

Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection techniques. Computer Science Review, 14(2), 201-221.

Kumar, R., Singh, R., & Nand, A. (2021). Predicting defects in software using machine learning: A survey. International Journal of Computer Applications, 175(5), 34-42.

Marinescu, R., & Mocanu, M. (2020). Inte-grating machine learning in software devel-opment for continuous testing. Journal of Software Maintenance and Evolution, 32(7), 52-68.

Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?” Explaining the predictions of any classifier. In Pro-ceedings of the 22nd ACM SIGKDD Inter-national Conference on Knowledge Discovery and Data Mining (pp. 1135-1144). ACM.

Zhang, J., Wu, Z., & Yang, X. (2020). An approach to defect prediction using machine learning: A case study on a large software project. IEEE Transactions on Software En-gineering, 46(8), 860-875.

Downloads

Published

15-05-2025

How to Cite

Alam, G. T., Bakhsh, M. M. ., Nadia, N. Y. ., & Islam, S. A. M. . (2025). Predictive Analytics in QA Automation:: Redefining Defect Prevention for US Enterprises. Journal of Knowledge Learning and Science Technology ISSN: 2959-6386 (online), 4(2), 55-66. https://doi.org/10.60087/jklst.v4.n2.005