Explainable AI (XAI) 2400-MIKRO-AIBF-XAI
The course consists of two parts - theoretical and practical, focusing on the development of Machine Learning models for classification problems, with an emphasis on best practices in business modelling.
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 modelling 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:
● Permutated Feature Importance
● Partial Dependence Profiles/Conditional Dependency Profiles/ Acummulated Local Effects
● Ceteris Paribus Profiles
● Oscillations
● Breakdown plots
The course will provide a comprehensive overview of XAI methods in DALEX in R, explaining their specific applications and best practices.
The project ‘Application of Artificial Intelligence in Business and Finance’ (No. BPI/SPI/2024/1/00078) is implemented by the University of Warsaw as part of the Spinaker programme organised by the National Agency for Academic Exchange (within the project ‘Wsparcie tworzenia i realizacji międzynarodowych programów kształcenia’, funded by the European Funds for Social Development 2021–2027).
Course coordinators
Micro-credential certificate
Learning outcomes
In terms of knowledge, the participant:
● knows and understands the importance of the interpretability of black-box models;
● understands the complete end-to-end process of developing a machine learning model;
● is familiar with Explainable Artificial Intelligence tools and understands their applications in a business environment.
In terms of skills, the participant:
● is able to apply XAI tools in a business environment;
● is able to correctly interpret the metrics and results produced by XAI methods;
● is able to contribute to the development of machine learning models in practice.
In terms of social competences, the participant:
● is prepared to use machine learning models responsibly, taking into account their interpretability, ethical considerations, and regulatory requirements;
● is prepared to collaborate effectively in the development and analysis of models.
Assessment criteria
Written assessment (post-test).
Bibliography
1. Biecek, P., & Burzykowski, T. (2021). Explanatory model analysis. Chapman and Hall/CRC. https://pbiecek.github.io/ema/
2. Molnar, C. (2022). Interpretable machine learning: A guide for making black box models explainable (2nd ed.). https://christophm.github.io/interpretable-ml-book/
3. Biecek, P. (2018). DALEX: Explainers for complex predictive models in R. Journal of Machine Learning Research, 19(84), 1–5.
4. Rai, A. (2020). Explainable AI: From black box to glass box. Journal of the Academy of Marketing Science, 48, 137–141. https://doi.org/10.1007/s11747-019-00710-9
5. Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., & Hussain, A. (2024). Interpreting black-box models: A review on explainable artificial intelligence. Cognitive Computation, 16(1), 45–74. https://doi.org/10.1007/s12559-023-10152-5
6. Gron, A. (2017). Hands-on machine learning with Scikit-Learn and TensorFlow: Concepts, tools, and techniques to build intelligent systems (1st ed.). O'Reilly Media, Inc.