Dennis Collaris
Computer Science & Engineering
Explainability of
Machine Learning models
Graduation project
Explainability of
Machine Learning models
Machine Learning
Cat!
Cat!
Cat!
Bunny!
Bunny!
Bunny!
→ Cat 🐈
→ Bunny 🐰
Classification
Decision Tree
Flappy ears?
Bunny 🐰
Yes
No
Wiggles nose?
Yes
No
Bunny 🐰
Cat 🐈
Use case: Fraud detection
for insurances
→ Non-fraud
Insurance policy
Insurance policy
→ Fraud
Fraud classification
Duration illness < 200 days
Non-fraud
Yes
No
Premium percentage < 5%
Yes
No
Non-fraud
Fraud
Fraud Decision Tree
Fraud Decision Tree
Fraud Random Forest
Fraud Random Forest
Difficult problem
7,582,365
decisions!
Currently: Black box
Policy
Fraud
Model
Non-fraud
Policy
Fraud
Model
Non-fraud
Because..
Duration illness > 200 days
Premium rate > 5%
Goal: White box
Global / Local
Literature
Literature
Structural
visualization
Model
simplification
Feature analysis
Literature
Structural
visualization
Model
simplification
Feature analysis
Feature importance
Feature
interaction
Sensitivity
analysis
Feature importance
Feature importance
Feature importance
Sensitivity analysis
Sensitivity analysis
| Policy | Duration illness | Premium rate |
|---|---|---|
| ANP128 | days | 5% |
300
250
200
150
100
50
1
0
1
300
200
100
0
Duration illness
Fraud?
Fraud
Non-fraud
Model simplification
Model simplification
Model simplification
Dashboards
Questions?
Thesis presentation (backup, cat/bunny, old)
By iamdecode
