Fitting and tuning decision trees, random forests, and gradient boosting models in R.
These are the key learning objectives for Decision Trees and Ensemble Methods on SOA Exam PA. Paraphrased from the public SOA syllabus — we recommend also checking the current syllabus on soa.org before your exam sitting.
Fit regression and classification trees using rpart in R
Tune random forests and gradient boosted trees for performance
Compare tree-based methods to GLMs for an actuarial problem
Upload your ACTEX Exam PA digital edition, scanned ASM pages, TIA handouts, or your own notes. exclam.ai extracts the Decision Trees and Ensemble Methods sections and generates flashcards automatically.
Generate multiple-choice quizzes specifically on Decision Trees and Ensemble Methods. Weak questions get re-surfaced until you get them right consistently.
Because Decision Trees and Ensemble Methods is 20–30% of your exam, losing it during review costs you. FSRS brings it back at the optimal moment.
SOA Exam PA has 4 topic areas. Decision Trees and Ensemble Methods is weighted at approximately 20–30% of the exam — here is where it sits relative to the other topics.
| Topic area | Weight |
|---|---|
| Problem Framing and Data Preparation | 15–25% |
| Generalized Linear Models | 30–40% |
| → Decision Trees and Ensemble Methods | 20–30% |
| Model Validation and Business Communication | 15–25% |
Translating a business problem into a predictive modeling question, exploratory data analysis, and feature engineering.
Building, evaluating, and interpreting GLMs in R for common actuarial applications.
Cross-validation, test set performance, sensitivity analysis, and communicating results to non-technical stakeholders.
Upload your ACTEX Exam PA digital edition, scanned ASM pages, TIA handouts, or your own notes. exclam.ai generates a fully guided study plan with adaptive flashcards and quizzes for this topic.