As The World Turns
summary
Claims a working pipeline that ingests JIRA ALM logs and application logs with Talend and Logstash, trains ML models on last 10 sprints using a 70/30 train/test split, and outputs risk scores to a live dashboard. Uses NLP to map user stories to past defects, clustering to pick representative test data, and classification to predict defects from new commits and prioritise high‑risk cases. Proof of concept includes automated intent checks for Alexa skills and early results that reduce defects found later.
AI-written summary · about
chapters (8)
- 0:00Start
- 7:44GENCE FROM DATA
- 9:52PATTERNS → PREDICTIONS
- 13:11INCIDENT PREDICTION
- 15:27TEST DATA PREDICTION
- 16:54REQUIREMENT PREDICTION
- 18:28DICTIONS DASHBOARD
- 21:51TABILITY OF PREDICTIONS
related talks
32mLightning Talks
44mThe Future is Today: Leveraging AI in Software Testing
33mShray Sharma: Leveraging AI for Self-Healing Tests: Current Capabilities and Future Prospects
16mTransforming Test Automation with AI and Machine Learning
41mUsing ML to find value in your automated tests
46mSW Testing: Can ML save us?
45mSpyros Katopodis: How You Should Be Using Agile and AI For Testing And Quality Assurance
28mML-Driven Test Intelligence at Scale - What Works What Fails and Why It Matters