Machine learning

Trending issue

Husky vs. Wolf problem

CycleGAN

75% risk!

Black box 

model

Domain expert

Data

Machine learning

Global

Instance-level

Fraud Dashboard

Overview

ExplainExplore

Global

Instance-level

Fraud Dashboard

Overview

ExplainExplore

Contribution-Value Plots

Global

Instance-level

Fraud Dashboard

Overview

ExplainExplore

CV Plots

Global

Instance-level

Fraud Dashboard

StrategyAtlas

Overview

Fraud detection explanations
sick-leave insurances

Data

• Missing/incorrect values

Model

• 100 Random Forest
• 500 trees each
• ~25 decisions per tree
• 1.312.471 decisions total!

Problem

My solution

Fraud team happy! 🎉

Any project using a Random Forest in R!

• Given a workshop for data science teams
• Code for dashboard available at team Leon

Applications

Paper presented at:
Workshop on Human Interpretability in Machine Learning

Stockholm, Sweden

Effectiveness of debt
collection strategies

Help data scientists to create and tune explanatory surrogate models.

My solution

Data scientists happy! 🎉

Anywhere where tabular data is used.

Any model in Python or PMML.

• Debtor management (Team Randy Soet)
• Discussing operationalization

Applications

Paper presented at:
IEEE Pacific Visualization 2020

@

Tianjin, China

Machine Learning Interpretability through Contribution-Value Plots

Pre-existing techniques as elementary building blocks.

Prediction (ŷ)

x

ŷ

How?

Pre-existing techniques as elementary building blocks.

[1]    Friedman, J. H. "Greedy function approximation: a gradient boosting machine.", 2001.

Prediction (ŷ)

Local PDP [1]

Sensitivity

analysis

x

ŷ

How?

Pre-existing techniques as elementary building blocks.

Prediction (ŷ)

Sensitivity

analysis

x

ŷ

[2]   Goldstein, A., et al. "Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation.", 2015.

Local PDP [1]

ICE plot [2]

Repeat

How?

Pre-existing techniques as elementary building blocks.

[4]   Lundberg, S. M., et. al.. "A unified approach to interpreting model predictions.". 2017.

Feature 1

Feature 2

Feature 3

Feature 4

Feature 5

[3]   Ribeiro, M. T., et. al. ""Why should i trust you?" Explaining the predictions of any classifier.", 2016.

How?

Pre-existing techniques as elementary building blocks.

Prediction (ŷ)

Sensitivity

analysis

x

ŷ

Local PDP [1]

ICE plot [2]

Repeat

How?

Pre-existing techniques as elementary building blocks.

Prediction (ŷ)

Local PDP

ICE plot

Contribution (β)

Sensitivity

analysis

Repeat

x

ŷ

x

β

How?

Pre-existing techniques as elementary building blocks.

Prediction (ŷ)

Local PDP

ICE plot

Contribution (β)

LCV plot

Sensitivity

analysis

Sensitivity

analysis

Repeat

x

ŷ

x

β

How?

How?

Pre-existing techniques as elementary building blocks.

Prediction (ŷ)

Local PDP

ICE plot

Contribution (β)

LCV plot

GCV plot

Sensitivity

analysis

Sensitivity

analysis

Repeat

Repeat

x

ŷ

x

β

Automatic acceptance of
car insurance applications

How?

The basic principle

How?

The basic principle

My solution

Data scientists happy! 🎉

Anywhere where tabular data is used.

Any model in Python or PMML.

• Schade en Inkomen (Team Wouter Slot)
• Discussing operationalization

Applications

Paper submitted to:
IEEE VIS 2021

@

New Orleans, LA, USA