Understanding Black-Box Models with Partial Dependence and Individual Conditional Expectation Plots

Показать описание

Ray Wright demonstrates methods for understanding the rationale behind the predictions that your complex machine learning models are providing.

SUBSCRIBE TO THE SAS SOFTWARE YOUTUBE CHANNEL

ABOUT SAS
SAS is a trusted analytics powerhouse for organizations seeking immediate value from their data. A deep bench of analytics solutions and broad industry knowledge keep our customers coming back and feeling confident. With SAS®, you can discover insights from your data and make sense of it all. Identify what’s working and fix what isn’t. Make more intelligent decisions. And drive relevant change. #SASSoftware

CONNECT WITH SAS

Рекомендации по теме

Комментарии

Thanks man! This was the most clear presentation video I found on the subject so far!

Dreaming-

You showed a variable importance table for a neural network model. How did you calculate it?

TheTigerli

3:27 - any intuitive/technical idea as to why random forest leads to such a different prediction from boosting here (referring to the drop)? Both use trees (I assume), and gradient boost is 'supposed' to be superior to rf. Thanks for the video!

paulgoethe

Understanding Black-Box Models with Partial Dependence and Individual Conditional Expectation Plots

Understanding Black-Box Models with Partial Dependence and Individual Conditional Expectation Plots

Partial Dependence Plots (Opening the Black Box)

xspliner: An R Package to Explain Black-Box Machine Learning Models

Understanding Your Machine Learning Model: Black Box No More — Gourab De (DataEDGE 2019)

Explaining Black-Box Models Through Counterfactuals | Patrick Altmeyer | JuliaCon 2022

How to Explain Your Black-Box Models in SAS Viya

Interpreting Black-Box Supervised Learning Models Via Accumulated Local Effects

EAGE Student E-Lecture: Cracking Open the Black Box by Jesper Sören Dramsch

SHAP Analysis : Understanding the Black Box

SAS Tutorial | Opening the Black Box of Model Interpretability in SAS Viya

How to interpret a black box ?

Open the Machine Learning Black-Box with modelStudio & Arena

07-102_Interpretable Machine Learning, making black box models explainable with Python!(David Low)

SHAP values for beginners | What they mean and their applications

Infoshare 2019: Adam Kaczmarek - Explain, explain, explain...: Interpretability of black-box (...)

Distributed Black-Box Model Explanation with Ray - Alexandru Coca, Seldon

Explaining Black-Box Machine Learning Predictions - Sameer Singh, UC Irvine

Interpreting Machine Learning Models in SAS Model Studio

Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models

Brian Lucena - Interpreting Black-Box Models with Applications to Healthcare - MLconf SF 2016

AI AUDITS: BLACK BOX VS. WHITE BOX PERSPECTIVES

Interpretable machine learning (part 2): ICE, partial dependency plots and surrogate models

DALEX will help you to understand this complex predictive model

Interpretable machine learning (part 1): Peeking into the black box