Computational Methods in Non-life Insurance

Course content

Some Bayesian theory. Standard and Monte Carlo based integration, including Laplace approximation and variational inference. Markov Monte Carlo methods  including Metropolis Hastings and Gibbs sampling. Some classical optimization methods. Simulated annealing and CMA-ES. EM-algorithm. Hyperparameter optimization.

Education

MSc Programme in Actuarial Mathematics
 

Learning outcome

Knowledge: Understand the difference between pure Bayesian and frequentist methods. Insight into a number of numerical methods to solve the relevant problems. Knowledge about choosing good hyperparameter values in complex models.

Skills: Be able to identify problems and formulate them mathematically. Also be able to either program the solutions oneself or find relevant programs elsewhere.

Competences: To be able to understand the principles behind the various methods,  including knowledge of their advantages and drawbacks. In addition the students will be able to run and understand the input and output of suitable programs in R. There will also be some focus on how to choose a good computational solution for a given task.

 

Lectures 5 hours a week. Additional exercise and homework sessions one hour a week.

Own notes

NMAB18001U Matematisk statistik (MatStat)
NMAK11022U Regression (Reg) or NMAB22011U Regression for Actuaries (RegAct)
Or similar.

Academic qualifications equivalent to a BSc degree is recommended.

ECTS
7,5 ECTS
Type of assessment
Oral examination, 30min
Type of assessment details
Without preparation.
Exam registration requirements

Two compulsory homeworks. They do not count for the grade. 

Aid
Without aids
Marking scale
7-point grading scale
Censorship form
External censorship
Re-exam

Oral exam, 30 minutes without preparation. The two  compulsory homeworks have to be turned in no later than three weeks before the reexam.

 

Criteria for exam assessment

In order to obtain the grade 12 the student should convincingly and accurately demonstrate the knowledge, skills and competences described under Learning outcome.

Part time Master and Diploma courses

  • Category
  • Hours
  • Lectures
  • 35
  • Preparation
  • 104
  • Theory exercises
  • 7
  • Project work
  • 40
  • Exam
  • 20
  • English
  • 206

Kursusinformation

Language
English
Course number
NMAK23002U
ECTS
7,5 ECTS
Programme level
Full Degree Master
Duration

1 block

Placement
Block 4
Schedulegroup
C
Capacity
No limit.
The number of seats may be reduced in the late registration period.
Studyboard
Study Board of Mathematics and Computer Science
Contracting department
  • Department of Mathematical Sciences
Contracting faculty
  • Faculty of Science
Course Coordinator
  • Jostein Paulsen   (7-6e737778696d72447165786c326f7932686f)
Saved on the 28-02-2023

Are you BA- or KA-student?

Are you bachelor- or kandidat-student, then find the course in the course catalog for students:

Courseinformation of students