Applications of Explainable AI in Predictive Modelling 2400-ZEWW947

The course consists of two parts, focusing on the development of Machine Learning models for both regression and classification problems, with an emphasis on best practices in business modeling.

For both problems, an end-to-end modelling pipeline will be covered:
• Data cleaning
• Data exploration
• Variable selection
• Feature engineering
• Model selection
• Parameter estimation
• Hyperparameter tuning
• Model validation

While it is assumed that participants are familiar with the machine learning modeling process, the key focus of the course will be an in-depth exploration of black-box models with the implementation of XAI methods. In particular, both instance-level and dataset-level exploration methods will be covered, including:
• Ceteris Paribus Profiles
• Partial Dependence Profiles
• Conditional Dependency Profiles
• Oscillations
• LIME
The course will provide a comprehensive overview of XAI packages such as DALEX and SHAP in both Python and R, explaining their specific applications and best practices.
Capstone Project:
At the end of the course, students will apply their knowledge through an end-to-end machine learning modeling project (either regression or classification) that includes model exploration with the discussed XAI methods. Additional elements include:
• GitHub collaboration
• Clean code practices
• Delivering a presentation on the model's outcome and interpretability.