Home▸Machine Learning & Neural Networks▸Explaining a Loan Model: Shapley Waterfall and Coalition Lattice (2D)

Explaining a Loan Model: Shapley Waterfall and Coalition Lattice (2D)

A waterfall that walks the model output from the average to this applicant, plus the 32-node coalition lattice coloured by mean output. Same shared model, Shapley enumeration and numerical checks as the 3D waterfall.

Machine Learning & Neural Networks2DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 3D version
Explaining a Loan Model: Shapley Waterfall and Coalition Lattice (2D) ↗ Open standalone

Open the black box of a small loan-approval model. Compute exact interventional Shapley values by enumerating all 32 feature coalitions, then compare them with occlusion, gradient times input and a LIME-style local surrogate on the same applicant. See why the methods agree on a linear model and disagree when features interact. Waterfall modelled in Blender, with six numerical checks built in.

⚙ Under the hood

A waterfall that walks the model output from the average to this applicant, plus the 32-node coalition lattice coloured by mean output. Same shared model, Shapley enumeration and numerical checks as the 3D waterfall.

Explainable AIShapley ValuesSHAPFeature AttributionLIME

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)