CYLGAug 10, 2021

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

arXiv:2108.07714v1
Originality Synthesis-oriented
AI Analysis

It addresses fairness and explainability issues for businesses using AI, but it is incremental as it reviews existing concepts and methods.

The paper tackles the problem of ensuring fairness and explainability in AI solutions for business, providing recipes for fairness and auditing algorithms with business use-cases.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes