English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This thesis explores open-sourced machine learning (ML) model explanationtools to understand whether these tools can allow a layman to visualize,understand, and suggest intuitive remedies to unfairness in ML-baseddecision-support systems. Machine learning models trained on datasets biasedagainst minority groups are increasingly used to guide life-altering socialdecisions, prompting the urgent need to study their logic for unfairness. Dueto this problem's impact on vast populations of the general public, it iscritical for the layperson -- not just subject matter experts in social justiceor machine learning experts -- to understand the nature of unfairness withinthese algorithms and the potential trade-offs. Existing research on fairness inmachine learning focuses mostly on the mathematical definitions and tools tounderstand and remedy unfair models, with some directly citing user-interactivetools as necessary for future work. This thesis presents FairLay-ML, aproof-of-concept GUI integrating some of the most promising tools to provideintuitive explanations for unfair logic in ML models by integrating existingresearch tools (e.g. Local Interpretable Model-Agnostic Explanations) withexisting ML-focused GUI (e.g. Python Streamlit). We test FairLay-ML usingmodels of various accuracy and fairness generated by an unfairness detectortool, Parfait-ML, and validate our results using Themis. Our study finds thatthe technology stack used for FairLay-ML makes it easy to install and providesreal-time black-box explanations of pre-trained models to users. Furthermore,the explanations provided translate to actionable remedies.

FairLay-ML: Intuitive Remedies for Unfairness in Data-Driven Social-Critical Algorithms