(in Polish) Sztuczna inteligencja w ubezpieczeniach 1000-1S22SIU
We shall cover the following topics:
1. Claim Frequency modeling using boosting and regression trees.
2. Practical aspects of using neural networks (NN) in the context of claim frequency modeling.
3. Nesting classical actuarial models using NN.
4. Theory and actuarial applications of the AdaBoost I XGBoost algorithms.
5. Survey of the actuarial applications of unsupervised learning.
6. Mortality modeling using recurrent NN.
7. NLP in insurance.
8. GLM vs. interpretable machine learning.
9. Application of convolutional neural networks in the context of mortality rates modeling.
10. Interpretable deep learning in actuarial modeling.
Type of course
Mode
Classroom
Prerequisites
Prerequisites (description)
Assessment criteria
Finał Grade based on the presentation delivered by the student.
Bibliography
Merz, Wuethrich, 'Statistical Foundations of Actuarial Learning and its Applications'
and other texts which we present during the first seminar
Additional information
Information on level of this course, year of study and semester when the course unit is delivered, types and amount of class hours - can be found in course structure diagrams of apropriate study programmes. This course is related to the following study programmes:
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: