Machine Learning-Driven Strategies for Optimizing Cloud-Based Regression Testing: Achieving Faster and More Reliable Releases

EasyChair Preprint 15028

Abstract

In the ever-evolving landscape of software development, the efficacy of regression testing is pivotal for ensuring reliable releases. Traditional regression testing approaches often struggle with inefficiencies and prolonged cycle times, especially in cloud-based environments where scalability and rapid deployment are key. This article explores innovative machine learning-driven strategies designed to optimize cloud-based regression testing. By leveraging advanced algorithms and predictive analytics, these strategies aim to enhance the accuracy and speed of regression tests. We discuss the integration of machine learning models that intelligently prioritize test cases, predict potential defects, and adapt testing processes based on historical data and real-time feedback. The application of these strategies not only accelerates the testing cycle but also improves the reliability of releases by focusing resources on high-impact areas. Our findings demonstrate that machine learning can transform regression testing from a bottleneck into a streamlined process, offering significant improvements in both efficiency and effectiveness in cloud-based environments.

Keyphrases: bottleneck, cloud-based, environments, learning, machine, streamlined, testing

@booklet{EasyChair:15028,
  author    = {Anthony Collins},
  title     = {Machine Learning-Driven Strategies for Optimizing Cloud-Based Regression Testing: Achieving Faster and More Reliable Releases},
  howpublished = {EasyChair Preprint 15028},
  year      = {EasyChair, 2024}}