Course curriculum

  • 1

    0. Getting started

  • 2

    1 - Introduction

  • 3

    2 - Data Collection

    • 2.1 - Introduction

    • 2.2 - Relevant Python Packages

    • 2.3 - Preliminary Analysis and Reshaping of Data

    • 2.4 - Conclusion

  • 4

    3 - Fitting Mortality Models

    • 3.1 - Introduction

    • 3.2 - Lee-Carter Model

    • 3.3 - Cairns-Blake-Dowd Model

    • 3.4 - Automating the Process

    • 3.5 - Conclusion

    • Week 1 Live Lesson: Chapter 1-3

  • 5

    4 - Forecasting

    • 4.1 - Introduction

    • 4.2 - Deterministic Forecasting: Lee-Carter

    • 4.3 - Deterministic Forecasting: Cairns-Blake-Dowd

    • 4.4 - Stochastic Forecasting: Lee-Carter

    • 4.5 - Stochastic Forecasting: Cairns-Blake-Dowd

    • 4.6 - Conclusion

  • 6

    5 - Forecasting Using an LSTM Neural Network

    • 5.1 - Introduction

    • 5.2 - Data Preparation

    • 5.3 - Theoretical Background

    • 5.4 - Fitting an LSTM using keras and tensorflow

    • 5.5 - Further Advances when Fitting an LSTM using keras and tensorflows

    • LSTM Notebooks, Lee-Carter & Cairns-Blake-Dowd Packages, and Dataset

    • Week 2: Forecasting and Introduction to LSTM Neural Networks

  • 7

    6 - Conclusion

    • 6.1 - Conclusion

  • 8

    Appendix and Further Resources

    • Python Conventions

    • New Developments of the Lee-Carter Model for Mortality (PDF)

    • Modelling and Management of Mortality Risk: A Review (PDF)

    • A Two-Factor Model for Stochastic Mortality with Parameter Uncertainty: Theory and Calibration (PDF)

    • Efficient Use of Data for LSTM Mortality Forecasting (PDF)

    • Mortality Forecasting using Stacked Regression Ensemble (PDF)

    • Monte Carlo Valuation of Future Annuity Contracts (PDF)

    • A Neural Network Extension of the Lee–Carter Model to Multiple Populations (PDF)

    • Time-Series Forecasting of Mortality Rates using Deep Learning (PDF)

    • LEE CARTER MODEL (CODE)

  • 9

    Downloadable Notebooks

    • Downloadable notebooks and data (zipped)