Python in Science Conference (SciPy)
Published July 10, 2025 | Version v1
Poster Open

Explaining ML predictions with SHAP

Authors/Creators

  • 1. Intuit, Inc., PyOpenSci

Contributors

  • 1. SLB
  • 2. Lawrence Berkeley National Laboratory
  • 3. Aptos
  • 4. Curvenote
  • 5. Arm
  • 6. Deloitte
  • 7. University of Alabama in Huntsville

Description

As machine learning models become increasingly accurate and complex, explainability has become essential to ensure trust, transparency, and informed decision-making. SHapley Additive exPlanations (SHAP) provide a rigorous and intuitive approach for interpreting model predictions, delivering consistent and theoretically grounded feature attributions. This article demonstrates the application of SHAP across two representative model types: boosted decision trees and neural networks.

Files

scipy-poster.pdf

Files (960.0 kB)

Name Size Download all
md5:4e3ed3d20827b2870995b09f049e5b45
960.0 kB Preview Download