Predict the Future with Watson Studio AutoAI
summary
Builds and deploys a real predictive model using Watson Studio AutoAI on the Titanic CSV, automatically generating eight pipelines with hyperparameter tuning and feature engineering and optimizing for ROC AUC. The demo shows which pipeline wins, displays feature importance (Sex ranks highest), saves a model, creates a web service with a scoring endpoint and bearer token, and returns a JSON prediction (example: 99.9% survival) ready for integration.
AI-written summary · about
chapters (19)
- 0:00Intro
- 3:50Getting Started
- 4:45Machine Learning
- 8:33Watson Studio
- 13:35IBM Cloud Login
- 18:05Create a New Project
- 20:35Data Sources
- 22:00What to Predict
- 23:10Experiment Settings
- 25:00Run Experiment
- 28:05Pipelines
- 32:00Top Ranking Pipeline
- 33:00Model Evaluation
- 35:00Model Deployment
- 37:00Implementation
- 38:10Testing
- 39:55Congratulations
- 40:25Resources
- 42:30Conclusion
related talks
39m"Would YOU Survive the Titanic?", with ML and .NET
54m"Would YOU Survive the Titanic?", with ML and .NET
51mHow to Test Artificial Intelligence and Machine Learning Solutions?
01h 05mAzure Machine Learning for the Developer
45mPredictive Computing: A.I. Gets Real
11mAutomation of AI: Accelerating the AI Revolution
39mBig Data Information Architecture for AI
31mAccelerating Your Analytics Journey With Real-time AI