# Artificial Intelligence and Deep Learning Models for Actuarial Applications

Lecture slides from UNSW’s ACTL3143 & ACTL5111 courses

## Overview

These are the lecture slides from my recent “Artificial Intelligence and Deep Learning Models for Actuarial Applications” courses (coded ACTL3143 & ACTL5111) at UNSW. They can be used to see what topics I covered in these courses. The slides are not intended to be used to learn deep learning from scratch. For that, you need to attend the lectures & complete the assessment.

## Lecture Materials

- Course Overview (slides)
- Artificial Intelligence (slides)
- Python (slides)
- Deep Learning with Keras (slides)
- Categorical Variables (slides)
- Classification (slides)
- Project (slides)
- Computer Vision (slides)
- Natural Language Processing (slides)
- Time Series & Recurrent Neural Networks (slides)
- Entity Embedding (slides)
- Optimisation (slides)
- Distributional Regression (slides)
- Interpretability (slides)
- Generative Networks (slides)
- Generative Adversarial Networks (slides)

## Readings

The readings from the book will come mainly from Géron (2022), which is available through the UNSW Library’s access to O’Reilly Media texts. I’ll give references to the 3rd edition, but if you get your hands on a copy of the 2nd edition then that is also fine. Some readings will be from James et al. (2021) (or equivalently the the Python version James et al. (2023)) which is available online; you’ll need the 2nd edition for this (the deep learning chapter is not in the 1st edition). Note, if I say “read from A up to B”, that means to read A but stop at B (without reading it).

Week | Readings |
---|---|

1 | Géron (2022): Chapter 1, Chapter 2 (up to “Handling Text and Categorical Attributes”), James et al. (2021): Sections 10.1 & 10.2 |

2 | Géron (2022): Chapter 2 (up to “Launch, Monitor, and Maintain Your System”), Chapter 3 (up to “Multilabel Classification”), Chapter 10 (“Implementing MLPs with Keras” up to “Building Complex Models Using the Functional API”) |

3 | James et al. (2021): Section 10.3, Géron (2022): Chapter 14 (just skim through the specific historical architectures, like InceptionNet etc.) |

4 | James et al. (2021): Section 10.4, Vajjala et al. (2020): Chapters 1 and 2 (up to “Modeling”) |

5 | James et al. (2021): Section 10.5, Géron (2022): Chapter 15, Hyndman & Athanasopoulos (2018): Section 5.1-5.3 and 5.8 |

7 | Géron (2022): Chapter 11, Chapter 13 “Encoding Categorical Features Using Embeddings” |

8 | Charpentier (2024), Molnar (2020), Barocas et al. (2023), O’Neil (2017). |

9 | Chollet (2021): Chapter 12 |

10 | - |

The following readings are for those who are taking ACTL3142/ACTL5110 at the same time as ACTL3143/ACTL5111 (or who just need to brush up on that course a little):

Week | Readings (ACTL3142 Revision) |
---|---|

1 | James et al. (2021): Chapter 2, Sections 3.1, 3.2, and 5.1.1 |

2 | James et al. (2021): Section 3.3.1, 4.1, 4.2, 4.3 |

Other useful resources include the Actuaries Institute’s Actuaries’ Analytical Cookbook and the Swiss Association of Actuaries’ Actuarial Data Science Tutorials.

## Contributors

- Tian (Eric) Dong
- Michael Jacinto
- Marcus Lautier
- Sam Luo
- Hang Nguyen
- Gayani Thalagoda

## Copyright

Patrick Laub

## References

*Fairness and machine learning: Limitations and opportunities*. MIT Press.

*Insurance, biases, discrimination and fairness*. Springer.

*Deep learning with Python*. Simon and Schuster.

*Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow*(3rd ed.). O’Reilly Media.

*Forecasting: Principles and practice*. OTexts.

*An Introduction to Statistical Learning: with Applications in R*. Springer.

*An Introduction to Statistical Learning: with Applications in Python*. Springer.

*Interpretable machine learning*.

*Weapons of math destruction: How big data increases inequality and threatens democracy*. Crown.

*Practical natural language processing: a comprehensive guide to building real-world NLP systems*. O’Reilly Media.