Introduction to R and Basic Data Analysis
ACTEX Learning - AFDP: R Session 2.1
Set-up
If you haven’t already, please download the material for this session from the Actuarial University Dashboard using the course link below: https://www.actuarialuniversity.com/seminar/View/14826. You’ll find a Session2.zip
file with all the necessary files. Make sure to unzip it in the same location of Session1.zip
.
Introduction to Predictive Modeling
In the first session of this course, we learned about the basics of R and how to perform basic data analysis. In this session, we will delve deeper into predictive modeling and practice using R functions in various actuarial contexts. We will also learn how to manage CSV files, explore R packages for data analysis, and apply our knowledge to a practical project.
Learning Objectives
- Utilize statistical modeling and simulation techniques
- Make R functions to use in various actuarial contests
- Practice managing csv files
- Learn about R packages for data analysis
- Apply learned R functions and concepts to a practical project
R is particularly suited for predictive modeling in actuarial work because it supports complex statistical analysis, has a vast collection of libraries (glm
, rpart
, randomForest
, survival
), and offers extensive visualization tools to communicate results effectively. Traditional statistical methods (like GLMs) and modern machine learning techniques (like Gradient Boosted Trees - GBMs and decision trees), can be implemented all within the same environment.
Examples
- Building a linear regression model to predict a company’s sales based on advertising spend.
- Using a decision tree to classify whether a customer will churn based on demographic and behavioral data.
Resources
- Applied Predictive Modeling by Max Kuhn and Kjell Johnson
- An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani
- Generalized Additive Models: An Introduction with R by Simon N. Wood