Leveraging machine learning for intelligent test automation: Enhancing efficiency and accuracy in software testing

Prathyusha Nama *, Harika Sree Meka and Suprit Pattanayak

Independent Researcher, USA.
 
Review
International Journal of Science and Research Archive, 2021, 03(01), 152–162.
Article DOI: 10.30574/ijsra.2021.3.1.0027
Publication history: 
Received on 10 January 2021; revised on 21 April 2021; accepted on 24 April 2021
 
Abstract: 
This paper discusses the possibility of applying machine learning (ML) and automation in the software testing process to improve the quality assurance process. The problem is that as software systems increase in size and functionality, more than traditional test approaches may be required, they become slow and error-prone. AI and ML can be used in software testing to reduce the manual approach and increase testing efficiency by improving testing quality. The work focuses on several AI-based approaches, including automated test case generation, intelligent test case prioritization, anomaly detection, and defect prediction. Real-life examples and studies show the effectiveness of these techniques in decreasing the time spent on manual testing, increasing the test precision, and increasing the system reliability. Nonetheless, the issues still open include the practicability of the proposed ML models, the training time, data sets, and the applicability of the entire framework across other software environments. This study shows how the testing process can be transformed with the help of AI-based testing, what issues may arise, and how further research can be conducted.
 
Keywords: 
AI/ML in Test Automation; Test Case Selection and Prioritization; Dynamic Test Case Generation and Adaptation; Test Execution Optimization; AI Powered Test Analysis
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0