GAM Coach: Towards Interactive and User-centered Algorithmic Recourse

Zijie J. Wang, Jennifer Wortman Vaughan, Rich Caruana, Duen Horng Chau
2/27/2023
cs.LGcs.AIcs.HC

No official code found. Best implementation: poloclub/gam-coach (19 stars, MIT, last commit 2023-10-03).

Abstract

Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/.

View on arXivView PDF

Code Implementations(1)

poloclub/gam-coachCommunity100%
MIT

Personal coach to help you obtain desired AI decisions!

193CSS, HTMLOct 5, 20213 years agoMIT
counterfactual-explanationsgeneralized-additive-modelsinteger-programminginteractive-visualizationsmachine-learning+2 more

Similar Papers

From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse

81% match2026

Counterfactual Generation with Answer Set Programming

80% match2024

From Search to Sampling: Generative Models for Robust Algorithmic Recourse

80% match1 repo12026

Tell Me a Story! Narrative-Driven XAI with Large Language Models

80% match1 repo92023

T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems

80% match2023

From Plan to Action: How Well Do Agents Follow the Plan?

79% match2026

Cite this paper

@article{wang2023coach,
  title  = {GAM Coach: Towards Interactive and User-centered Algorithmic Recourse},
  author = {Zijie J. Wang and Jennifer Wortman Vaughan and Rich Caruana and Duen Horng Chau},
  year   = {2023},
  eprint = {2302.14165},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.14165v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.14165.svg)](https://codeofpaper.com/paper/2302.14165)

Discussion