Categories
- ACTUARIAL DATA SCIENCE
- AFIR / ERM / RISK
- ASTIN / NON-LIFE
- BANKING / FINANCE
- DIVERSITY & INCLUSION
- EDUCATION
- HEALTH
- IACA / CONSULTING
- LIFE
- PENSIONS
- PROFESSIONALISM
- Thought Leadership
- MISC
Using machine learning (AI) model interpretation techniques, feature importance can be calculated. However, with conventional AI, feature importance variation significantly each time it is calculated, making comparisons difficult. In order to make use of this feature importance, the recently introduced TabNet model is used to capture the variation in feature importance.
0 Comments
There are no comments yet. Add a comment.