Home

The Model Fingerprint

URL
https://www.youtube.com/watch?v=bLN9WzPU_zg
Views
7
Description
Join the reading group: https://hudsonthames.org/reading-group/ The first lecture from the Hudson and Thames Reading Group, focuses on a model interpretability algorithm known as the model fingerprint, first published in the Journal of Financial Data Science. The algorithm decomposes model predictions into linear, nonlinear, and interaction components and studies a model’s predictive efficacy using the same components. Together, this forms a fingerprint to summarize key characteristics, similarities, and differences among different models.
Rating
0
Name
Hudson & Thames
Date
2022/09/26
TOP