Course Contents

  • 1

    0. Welcome

    • 1. Welcome to Industry Resource Library

    • 2. Contents and References

  • 2

    1. Problem Specification

    • 1. Insurance Data Science.Org Conference References (Ref 1.1)

    • 2. Practical Data Science for Actuarial Tasks (Ref 1.2)

    • 4. An article on The Use of Predictive Analytics in the Canadian Life Insurance Industry (Ref 1.4)

    • 6. Practical Application of Machine Learning within Actuarial Work (Ref 1.6)

    • 7. IFoA Data Science in Insurance - Some introductory case studies (Ref. 1.7)

    • 8. ADS Actuarial Data Science An initiative of the Swiss Association of Actuaries (Ref 1.8)

    • 9. A report on Machine learning in UK financial services by Bank of England (Ref 1.9)

  • 3

    2. Data Collection and Management

    • 1. Titanic : Who do you think survived Analysis (Ref 2.1)

    • 2. Singapore Actuarial Society Data Analytics Committee Information and Resources (Ref 2.2)

    • 3. Predicting the probability of a Severe bodily injury in a Car accident in Tel Aviv (Ref 2.3)

    • 8. ADS Actuarial Data Science An initiative of the Swiss Association of Actuaries (Ref 2.8)

    • 9. IFoA Data Science in Insurance - Some Introductory Case Studies (Ref 2.9)

    • 10. PyMC3 Examples: GLM with Custom Likelihood for Outlier Classification (Ref 2.10)

    • 11. Milliman Data Science Survey Report (Ref 1.11)

  • 4

    3. Model Building & Model Validation

    • 1. Contingencies Article - Model Behavior—Applications of Artificial Intelligence in Actuarial Science (Ref 3.1)

    • 2. AI and Automation Working Party – Short Term Output by AI and Automation Working Party (Ref 3.2)

    • 3. Abstract on Synthetic Data and Artificial Neural Networks for Insurance Loss Reserving (Ref 3.3)

    • 4. Methodology to train neural networks to perform non-life reserving projections from triangulated loss data (Ref 3.4)

    • 7. The Actuary and IBNR Techniques: A Machine Learning Approach (Ref 3.7)

    • 8. Machine Learning Cheat Sheet (Ref 3.8)

    • 9. Insurance risk pricing with XGBoost (Ref 3.9)

    • 11. Mind the Gap - Safely Incorporating Deep Learning Models into the Actuarial Toolkit by Ronald Richman (Ref 3.11)

    • 12. IFoA Non-life Machine Learning Resources (Ref 3.12)

    • 13. Kaggle Competition – Modelling of claims costs (Ref 3.13)

    • 14. Proxy Modelling using Machine Learning: LSMC case study (Ref 3.14)

    • 15. Machine learning in Reserving Working Party - UK survey findings (Ref 3.15)

    • 16. ADS Actuarial Data Science An initiative of the Swiss Association of Actuaries (Ref 3.16)

    • 17. Predicting the probability of a Severe bodily injury in a Car accident in Tel Aviv (Ref 3.17)

    • 18. IFoA Data Science in Insurance - Some introductory case studies (Ref 3.18)

    • 19. GAMs, GLMs and GBMs in insurance pricing (Ref 3.19)

    • 20. IFOA: General Insurance Machine Learning in Reserving working party (Ref 3.20)

    • 21. HDtweedie: The Lasso for the Tweedie's Compound Poisson Model Using an IRLS-BMD Algorithm (Ref 3.21)

    • 22. Local GLMnet: Interpretable Deep Learning (Ref 3.22)

    • 23. Road testing: Machine learning and the efficiency of fraud detection (Ref 3.23)

    • 24. Machine learning modelling on triangles - A worked example (Ref 3.24)

    • 25. 'HDTweedie' package - Motor Insurance Dataset (Ref 3.25)

    • 27. Machine learning in UK financial services -Bank of England (Ref 3.27)

    • 28. Statistical Foundations of Actuarial Learning and its Applications

    • 29. APR Modelling: Inheriting Actuarial Code

    • 30. The next generation of pricing: AutoML

  • 5

    4. Visualisation

    • 1. Blog Post - Data Visualisation (OK, boomer!) (Ref 4.1)

    • 2. Data visualisation as a powerful means of communication (Ref 4.2)

    • 4. Predicting the probability of a Severe bodily injury in a Car accident in Tel Aviv (Ref 4.4)

  • 6

    5. Deployment

    • 1. AI and Automation Working Party – Short Term Output by AI and Automation Working Party (Ref 5.1)

    • 2. SOA: Actuarial Modeling Systems (Ref 5.2)

    • 3. APR Modelling: Inheriting Actuarial Code

    • 4. The next generation of pricing: AutoML

  • 7

    6. Reporting/Explainability

    • 1. Report on Probability and Regression in Python and R (Ref 6.1)

    • 2. Why to Buy Insurance? An Explainable Artificial Intelligence Approach (Ref 6.2)

    • 3. SoA & Deloitte Research on Emerging Technologies and their Impact on Actuarial Science (Ref 6.3)

    • 4. SOA Research on Interpretable Machine Learning for Insurance (Ref 6.4)

    • 5. Most popular programming languages (2004 to 2021) (Ref 6.5)

    • 6. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable - Christoph Molnar, 2020-10-11 (Ref 6.6)

    • 7. ADS Actuarial Data Science An initiative of the Swiss Association of Actuaries (Ref 6.7)

    • 8. Titanic : Who do you think survived Analysis (Ref 6.8)

    • 9. Understanding Model Parameters From A Previously Fitted Model in R (Ref 9.6)

  • 8

    7. Practical Tips in R

    • 1. An Introduction to R: Examples for Actuaries by Nigel De Silva 28 Jan 2006 (Ref 7.1)

    • 2. The caret Package - Max Kuhn, 2019-03-27 (Ref 7.2)

    • 3. R-Bloggers (Ref 7.3)

    • 4. R documentation (Ref 7.4)

    • 5. METACRAN (Ref 7.5)

    • 6. Machine learning modelling on triangles - A worked example (Ref 7.6)

    • 7. Cran Task View (Ref 7.7)

    • 8. R Graph Gallery (Ref 7.8)

    • 9. R and RStudio Guides (Ref 7.9)

    • 10. New Sections for R-studio and Jupyter Notebooks (Ref 7.10)

    • 11. R Datasets(Ref 7.11)

    • 12. Text Mining with R (Ref 7.12)

    • 13. TensorFlow and Keras in R (Ref 7.13)

    • 15. RStudio Cheatsheets (Ref 7.15)

    • 14. IFoA Guide - Get up and running with R (Ref 7.14)

    • 16. StackOverflow (Ref 7.16)

    • 17. Understanding Model Parameters From A Previously Fitted Model in R (Ref 7.17)

    • 18. R for Data Science Website (Ref 7.18)

    • 19. Integrating R and SQL Queries (Ref 7.19)

    • 20. The tidyverse style guide(Ref 7.20)

    • 21. Cran R Project - Package ‘insuranceData’ February 20, 2015 (Ref 7.21)

    • 22. Data wrangling, exploration, and analysis with R (Ref 7.22)

    • 23. 'HDTweedie' package - Motor Insurance Dataset (Ref 7.23)

  • 9

    8. Practical Tips in Python

    • 1. PyMC3 Examples: GLM with Custom Likelihood for Outlier Classification (Ref 8.1)

    • 2. Open Actuarial group providing guidance to open approaches to actuarial problems (Ref 8.2)

    • 3. Python: Examples of AutoML Libraries (Ref 8.3)

    • 4. Predictive Analytics with Python: Case Study of the Insurance Industry (Ref 8.4)

    • 5. Tasting Python Machine Learning : Insurance Claim Prediction (Ref 8.5)

    • 6. Pyliferisk Examples (Ref 8.6)

    • 8. lifelib: Actuarial models in Python (Ref 8.8)

    • 9. ML modelling on triangles - a Python example (Ref 8.9)

    • 10. Python and Finance – Power Up Your Spreadsheets (Ref 8.10)

    • 11. Tools for Working with Excel and Python (Ref 8.11)

  • 10

    9. Practical Tips in GIT

    • 1. Git: Branches, Merges, Remotes and Git Intermediate Techniques (Ref 9.1)

    • 2. Version Control with Git (Ref 9.2)

    • 3. Pro GIT Book (Ref 9.3)

    • 4. GitHub (Ref 9.4)

  • 11

    10. Practical Tips in SQL

    • 1. Integrating R and SQL Queries (Ref 10.1)

  • 12

    11. Wider Themes

    • 1. Tesla AI Day (Ref 11.1)

    • 2. A Decentralised Future for Financial Technologies (Ref 11.2)

    • 3. Longevitas Survival Modelling (Ref 11.3)

    • 4. RPD Toolkit: Climate Change and Sustainability (Ref 11.4)

    • 5. Road testing: Machine learning and the efficiency of fraud detection (Ref 11.5)

    • 6. Leading Experts Reflect on the use of Data during the Pandemic (Ref 11.6)

    • 7. Python and Finance – Power Up Your Spreadsheets (Ref 11.7)

    • 8. New Risk On The Block - Climate Risk & Sustainability: A Crash Course For Actuaries

    • 9. Actuaries Climate Index

    • 10. Multi-Impact Growth Fund Annual Report

    • 11. Impact Report

  • 13

    12. Regulation & Governance

    • 1. Machine learning in UK financial services -Bank of England (Ref 12.1)

    • 2. IFOA's: The Actuaries' Code (Ref 12.2)

    • 3. IFoA APS X1: Applying Standards to Actuarial Work (Ref 12.3)

    • 4. IFoA APS X2: Review of Actuarial Work (Ref 12.4)

    • 5. IFoA: Actuarial Software and Calculations - Professional Responsibilities (Ref 12.5)

    • 6. IFoA Risk Management in a Digital World working party's paper on blockchain (Ref 12.6)

    • 7. IFoA: A Guide for Ethical Data Science (Ref 12.7)

    • 8. IFoA: Ethical and professional guidance on Data Science (Ref 12.8)

    • 9. IFoA: Guidance on the application of Technical Actuarial Standard 100 (Ref 12.9)

    • 10. FRC: Technical Actuarial Standard 100: Principles for Technical Actuarial Work (Ref 12.10)

    • 11. FRC: Technical Actuarial Standard 200: Insurance (Ref 12.11)

    • 12. AAE: European Standards of Actuarial Practice 1 (Ref 12.12)

    • 13. AAE: European Standards of Actuarial Practice 2 (Ref 12.13)

    • 14. AAE: European Actuarial Note 1 on ESAP 3 and ORSA (Ref 12.14)

    • 15. AAE: European Actuarial Note 2 on Actuarial Function under IORP II (Ref 12.15)

    • 16 . ASSA: APN 901: General Actuarial Practice (Ref 12.16)

    • 17. ASSA: COVID-19 Considerations for Life Assurance Actuaries (Ref 12.17)

    • 18. ASSA: APN 401- Establishing Technical Provisions for Short-Term Insurers (Ref 12.18)

    • 19. EU Artificial Intelligence Act: The European Approach to AI (Ref 12.19)

    • 20. Data Privacy- POPIA and the insurance industry (RSA) (Ref 12.20)

    • 21. Data Privacy- General Data Protection Regulation (GDPR) (Ref 12.21)

    • 22. SOA regulation: Actuarial Data Science Portal (Ref 12.22)