Welcome to the workshop!
Workshop
In ProgressWelcome to Advanced Feature Engineering for Time-Series Data!
Today's icebreaker:
The worst prediction ever!
Predictions about the future don’t always go as planned. Can you think of a personal, historical or pop culture prediction that was completely wrong?
Share your best response in the chat!
Today's agenda:
- **Review:**Recap key concepts.
- **Practise:**Time-series features for energy prediction.
- **Closing:**Key takeaways and next steps.
Today's learning objectives:
- Create time-based features from raw timestamp data to capture temporal patterns and improve predictive model performance.
- Incorporate domain-specific contextual data into feature engineering to enhance model relevance and accuracy.
- Apply feature selection or dimensionality reduction techniques to optimise model performance when working with a large number of engineered features.
- Explain how engineered features would be maintained and monitored in a production environment to ensure continued model performance.