The Future is Today: Leveraging AI in Software Testing
summary
Shows a concrete project: exported 490 Jira tickets, cleaned text, used bag‑of‑words and standard classifiers (KNN/Naive Bayes) to predict severity, initial confusion matrix gives about 73% accuracy and after merging medium/low classes reaches 82% accuracy. Demonstrates other usable tools and patterns: NLP for test‑step and data generation, outlier detection on execution durations, a visual locator approach (test.ai) for resilient UI selectors, and ideas for self‑healing and migration that actually reduce manual effort.
AI-written summary · about
chapters (8)
- 0:00AI in software testing
- 4:00Machine learning in testing
- 14:58ML test automation
- 27:10AI for UI automation
- 31:27ML in test execution
- 35:06Bug severity case study
- 41:13Future of AI testing
- 42:38Q&A
related talks
25mFuture of Software Testing: Machine Learning Assistance
40mFrom Bugs to Brilliance: Leveraging AI in Modern Software Testing
44mHow AI is Exposing the Existential Crisis of Software Testing
01h 04mImpact of AI on #SoftwareTesting: Are Testers Ready? 🔮
01h 05mPanel Discussion - The Future of Testing: Impact of AI in Quality Assurance and Beyond
25mWhat’s Our Job When The Machines Do Testing?
16mTransforming Test Automation with AI and Machine Learning
41mHow AI is transforming software testing