Hybrid Machine Learning Framework For Test Case Generation

Authors: Abhinav Balasubramanian

DOI: https://doi.org/10.5281/zenodo.14565859

Short DOI: https://doi.org/g8w628

Country: USA

Full-text Research PDF File:   View   |   Download

Abstract: Automated test case generation is an essential process in software testing, ensuring effective quality assurance while reducing manual effort. However, existing approaches face challenges such as limited scalability, insufficient test coverage, and difficulty in adapting to evolving software requirements. These issues hinder the effectiveness of both traditional methods and standalone machine learning (ML)-based solutions.
To address these challenges, we propose a Hybrid Machine Learning Framework that synergizes rule-based systems with advanced ML techniques. This framework combines the reliability of traditional methods with the adaptability and intelligence of supervised and reinforcement learning models. By leveraging this hybrid approach, the framework aims to improve test case generation processes through enhanced adaptability, prioritization, and dynamic response to software changes.
This study explores the potential of hybridizing traditional and ML-driven techniques to overcome existing limitations and sets the foundation for future work in automated software testing research.

Keywords: Artificial Intelligence (AI), Hybrid Machine Learning, Test Case Generation, Software Testing Automation, Software Quality Assurance, Scalable Testing Frameworks.

Paper Id: 231925

Published On: 2021-10-05

Published In: Volume 9, Issue 5, September-October 2021

Cite This: Hybrid Machine Learning Framework For Test Case Generation - Abhinav Balasubramanian - IJIRMPS Volume 9, Issue 5, September-October 2021. DOI 10.5281/zenodo.14565859

Share this