DeepAI AI Chat
Log In Sign Up

Harnessing value from data science in business: ensuring explainability and fairness of solutions

08/10/2021
by   Krzysztof Chomiak, et al.
0

The paper introduces concepts of fairness and explainability (XAI) in artificial intelligence, oriented to solve a sophisticated business problems. For fairness, the authors discuss the bias-inducing specifics, as well as relevant mitigation methods, concluding with a set of recipes for introducing fairness in data-driven organizations. Additionally, for XAI, the authors audit specific algorithms paired with demonstrational business use-cases, discuss a plethora of techniques of explanations quality quantification and provide an overview of future research avenues.

READ FULL TEXT

page 28

page 34

page 41

06/08/2022

Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models

Motivations for methods in explainable artificial intelligence (XAI) oft...
03/03/2021

Fairness and Robustness of Contrasting Explanations

Fairness and explainability are two important and closely related requir...
05/31/2018

Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning

There has recently been a surge of work in explanatory artificial intell...
12/07/2022

Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations

While machine learning models have achieved unprecedented success in rea...
02/17/2023

Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions

Ensuring trustworthiness in machine learning (ML) models is a multi-dime...
07/22/2022

Algorithmic Fairness in Business Analytics: Directions for Research and Practice

The extensive adoption of business analytics (BA) has brought financial ...
07/08/2022

An Approach to Ensure Fairness in News Articles

Recommender systems, information retrieval, and other information access...