Machine learning

75% risk!

Black box 

model

Domain expert

Data

Machine learning

Global

Local

Overview

ExplainExplore

Global

Local

Fraud Dashboard

Overview

ExplainExplore

Contribution-Value Plots

Global

Local

Fraud Dashboard

Overview

ExplainExplore

CV Plots

Global

Local

Fraud Dashboard

StrategyAtlas

Overview

Fraud detection explanations
for sick-leave insurances

Data

 

 

 

 

 

 

 

 

• Missing/incorrect values

Model

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

Real world scenario

My solution

[1] Palczewska, Anna et. al. Interpreting random forest classification models using a feature contribution method. In Integration of reusable systems, pp. 193–218. Springer, 2014.

0              1               2              3             x

y

2

1

 

7 : 7

Feature contribution

[2] Friedman, Jerome H. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5): pp. 1189–1232, 2001. 

0%

100%

200

100

0

Duration illness

Company	ABC Inc
Employees	5
Duration illness	days
...	...

Partial dependence

[3] Ribeiro, Marco Tulio et. al. Why should i trust you?: Explaining the predictions of any classifier. In

Proceedings of the 22nd ACM SIGKDD, pp. 1135–1144. ACM, 2016.

[4] Deng, Houtao. Interpreting tree ensembles with inTrees. arXiv preprint arXiv:1408.5456 , pp. 1–18, 2014.

0              1               2              3             x

y

2

1

 

Local rule extraction

Fraud team happy! 🎉

Paper presented at:
Workshop on Human Interpretability in Machine Learning

Stockholm, Sweden

Questions?

Visual exploration of
machine learning explanations

Surrogate learning

0              1               2             3             x

y

2

1

 

Problem

Help data scientists to create and tune explanatory surrogate models.

• ← Any tabular data set

• ← Any Python classifier, or PMML

• ← Different surrogate models

Configuration view

• ← Surrogate fidelity: R2
• ← Prediction
• ← Feature contribution

• Shows values  or contribution →
• Line color = predicted class →
• Compare selected instance with data →
• Clusters indicate ‘strategies’ →

Feature view

Context view

Context view

Context view

Use case

Paper accepted at:
IEEE Pacific Visualization 2020

@

Tianjin, China

 

Questions?

More info at

explaining.ml

Applications

Paper and software submitted to:
Journal of Machine Learning Research
 

Machine Learning Open Source Software (MLOSS)

 

 

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

Wine acidity (pH)

x

β

An exemplary data model exploration

Data

• 998 red wines
• 11 features

Model

• Random Forest (100 trees)
• Predict quality: 👍 / 👎

An exemplary data model exploration

x

β

x

β

An exemplary data model exploration

An exemplary data model exploration

Line fading .      .

x

β

Questions?

More info at

explaining.ml

Strategy analysis for
machine learning interpretability

How?

The basic principle

My solution

Paper accepted and in press at:
IEEE Transactions on Visualization and Computer Graphics

 

 

More info at

explaining.ml

Questions?