---
title: "Visual Analytics for Guiding Feature Attribution Method Selection"
authors:
  - "Priscylla Silva"
doi: "10.24963/ijcai.2025/1243"
url: "https://ijcai.org/proceedings/2025/1243"
pdf: "https://ijcai.org/proceedings/2025/1243.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10977-10978"
track: "Doctoral Consortium"
keywords:
  - "AI Ethics, Trust, Fairness: ETF: Explainability and interpretability"
  - "AI Ethics, Trust, Fairness: ETF: Trustworthy AI"
---

# Visual Analytics for Guiding Feature Attribution Method Selection

Priscylla Silva

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10977-10978. DOI: [10.24963/ijcai.2025/1243](https://doi.org/10.24963/ijcai.2025/1243)

## Abstract

Feature attribution methods explain model predictions by assigning importance to input features. Choosing the most suitable method is difficult due to inconsistencies and a lack of universal solutions. Our research focuses on proposing tools and methodologies for evaluating, comparing, and selecting these methods.