Welcome to the workshop!

Workshop

In Progress

Welcome to Evaluating Model Performance with Ensemble Methods!

Today's icebreaker:

Share one instance where accurate predictive modeling influenced a business decision you’ve seen or read about.

Put you answers in the chat.

Today's agenda:

ReviewRecap key concepts from async units 1 and 2.15 minsDemoWe'll provide a guided walkthrough of how to:

• Prepare and clean your data.

• Train ensemble classifiers such as Random Forest, Gradient Boosting, XGBoost.

• Apply the hyperparameter optimisation techniques GridSearchCV and RandomizedSearchCV. 10 minsPracticeYou'll get hands-on with the ensemble methods for model evaluation shown in the demo.25 minsClosingKey takeaways and next steps.10 mins## Today's learning objectives:

• Implement and interpret ensemble methods** **(Random Forest, Gradient Boosting, XGBoost) for classification tasks, identifying their relative strengths in improving predictive accuracy.

• Evaluate ensemble model performance rigorously using metrics including accuracy, precision, recall, and confusion matrices, effectively communicating results.

• Apply hyperparameter tuning techniques (GridSearchCV, RandomizedSearchCV) to optimise ensemble classifiers for specific business contexts.

• Make data-driven recommendations based on ensemble model evaluations, effectively translating technical results into actionable business strategies, specifically in customer-retention scenarios.