Table of Contents

• Machine Learning Applications in Actuarial Science and Risk Management
  • About
  • Course Description
    • Code and Notebooks
  • Schedule
  • References

Machine Learning Applications in Actuarial Science and Risk Management

About

This site is a collection of resources for the course Machine Learning Applications in Actuarial Science and Risk Management. Please refer to the course syllabus for more information on the course content and schedule.

Course Description

In this course, we will explore the application of machine learning algorithms in actuarial science and risk management through common use cases such as:

• Time series modeling
• Marketing campaign predictions
• Insurance claim predictions
• Credit risk modeling
• Operational risk modeling and fraud detection
• Natural Language Processing (NLP) and information extraction

We will begin each topic with an overview of the theoretical foundations of relevant statistical and machine learning models. Discussions will cover the pros and cons of each model, best practices for model selection and evaluation, and case studies demonstrating their real-world applications. For some classical models, we will also implement key algorithms from scratch to deepen our understanding. This approach aims to provide students with a comprehensive grasp of both the theoretical and practical aspects of these models.

Code and Notebooks

• Notebooks and code examples could be viewed via

Schedule

• Spring 2025: RMI 8450 (Online) Monday 7:15 pm - 9:45 pm [syllabus]

References

We don't have a required textbook for this course. However, the following books are recommended for students who want to dive deeper into the topics covered in this course. I'll also highlight the chapters that are relevant to the topics we cover in class while we progress through the semester.

• Hands-On Machine Learning with Scikit-Learn and TensorFlow O’Reilly Media, 3rd Edition by Aur´elien G´eron
  • Released October 2022
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781098125974
• An Introduction to Statistical Learning, with Application in Python
  • Published July 5, 2023 [link]
  • Publisher(s): Springer
  • ISBN: 9783031387463
  • The lab section of each chapter is implemented in Python. The resources link on the book homepage www.statlearning.com provides jupyter notebooks of these labs as well [resources]
• Machine Learning for Financial Risk Management with Python
  • Published December 2021
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781492085256
• Deep Credit Risk: Machine Learning with Python (TBD)
  • Published June 2020
  • Publisher(s): Independently published
  • ISBN: 9798617590199