Machine Learning Methods in Non-Life Insurance

Course content

Basic theory of penalized linear regression, additive models, generalized additive models, some machine learning regression methods, Cox regression and regression trees.

Education

MSc Programme in Actuarial Mathematics

Learning outcome

Knowledge:

  • Standard penalized methods such as ridge regression and the lasso
  • Know splines, additive and generalized additive models.


Skills:

  • Some machine learning regression methods such as projection pursuit regression, neural networks, MARS and boosting.
  • Know the basics of Cox regression
  • Know about different regression tree models such as CART, random forest and how to boos a regression tree.


Competences:

  • Know how to use R to solve practical problems

4 hours of lectures per week for 7 weeks

See Absalon for a list of course literature.

Non-life insurance 2 (Skade 2) or similar.

ECTS
7,5 ECTS
Type of assessment
Oral examination, 30 minutes under invigilation
Half time used to present a randomly chosen topic from a list of questions available before the exam. There will be no preparation time.
Aid
Without aids
Marking scale
7-point grading scale
Censorship form
External censorship
One external examiner.
Criteria for exam assessment

The student must in a satisfactory way demonstrate that he/she has mastered the learning outcome of the course.

Single subject courses (day)

  • Category
  • Hours
  • Exam
  • 1
  • Preparation
  • 135
  • Lectures
  • 28
  • Project work
  • 42
  • English
  • 206