Exam SRM – Statistics for Risk Modeling
5 个单元 · 29 个章节
免费 Exam SRM – Statistics for Risk Modeling 学习笔记，适合 SOA (Society of Actuaries) 学生。每个章节都覆盖一个重点主题，并附例题与可延伸到 thinka app 的练习提示。
Basics of Statistical Learning
Supervised vs. unsupervised and regression vs. classification
Assessing model accuracy
The bias-variance tradeoff
Training set vs. test set validation
k-fold cross-validation
Leave-one-out cross-validation
Linear Models
Ordinary least squares vs. generalized linear model assumptions
The exponential family and link functions
Interpreting parameters in a business context
Diagnostic tests of model fit and assumption checking
Variable transformations and interactions
Model selection criteria: t and F tests, AIC, BIC, and likelihood ratio test
Predicted values, confidence intervals, and prediction intervals
Regularized regression and K-nearest neighbors
Time Series Models
Stochastic time series: random walks, stationarity, and autocorrelation
Exponential smoothing models
Autoregressive models
Autoregressive conditionally heteroskedastic models
Predicted values and confidence intervals
Decision Trees
Constructing and pruning decision trees
Classification trees
Regression trees
Bagging, boosting, and random forests
Comparing decision trees to linear models
Unsupervised Learning Techniques
Principal components and how they are calculated
Interpreting principal components analysis
K-means clustering
Hierarchical clustering
Deciding the number of clusters
看完笔记了？现在就用 AI 题目测一测自己。
马上练这一题