Looking for a different project? Check out one of my other works here:

Strategy Atlas
Strategy Analysis
for Machine Learning

StrategyAtlas is a visual analytics system to enable understanding of complex models
by identifying and interpreting different model strategies.

model⋅strategy [ˈmɒdl ˈstratɪʤi]


  1. different treatments by a machine learning model of distinct groups in the input data.

As an example, consider a fraud detection model.

How do we find data clusters?

Traditionally, we can find clusters in the data by applying a 2D projection technique (e.g., UMAP).



How do we find strategy clusters?

We propose using the same approach on feature importance values to find model strategies.



What does a cluster mean?

Clusters in the StrategyMap indicate model strategies. However, what does each of these clusters mean?
Our proposed visual analytics system StrategyAtlas offers three methods to identify and interpret model strategies:

Gradient heat map

A gradient heat map enables seeing how the feature contribution values of a single feature are distributed in the projection space.

Density plot list

Interactive density plots enable the analysis of clusters in terms of multiple features at a glance.

Cluster view

The cluster view helps to understand strategy clusters by representing them as a decision tree (separating the cluster from the other data).

Check demo video

To see how StrategyAtlas enables understanding complex machine learning models, check out the demo video:

Or try out the online demo.


If you want to refer to our system, please cite our paper using the following BibTeX entry:

  author={Collaris, Dennis and Van Wijk, Jarke J.},
  journal={IEEE Transactions on Visualization and Computer Graphics},
  title={StrategyAtlas: Strategy Analysis for Machine Learning Interpretability},