Fairness in Machine Learning Workshop

Fantastic Introductions to Machine Learning!

http://www.r2d3.us/ (A couple of really good visualizations to understand some of the issues related to models based on the simple decision tree algorithm)

https://research.google.com/bigpicture/attacking-discrimination-in-ml/

https://speak-statistics-to-power.github.io/fairness/

https://github.com/dynamicwebpaige/runconf18

Resources

Building Ethical Algorithms by Center for Democracy & Technology https://github.com/numfocus/algorithm-ethics/blob/master/EthicalAlgorithmTool.md

Module I: COMPAS

Compass Analysis by ProPublica

Data and analysis for ‘Machine Bias’

COMPASDataEthics by Pranav Mayuram https://github.com/pranavmayuram/COMPASDataEthics

FairML by Julius Adebayo https://github.com/adebayoj/fairml

Aequitas by the Center or Data Science and Public Policy

machLearn by David Stephens


Module II: Predictive Policing

HunchLab

https://www.hunchlab.com/resources/

Predictive Policing Studies

http://www.jratcliffe.net/research/the-philadelphia-predictive-policing-experiment/

https://www.nature.com/news/reform-predictive-policing-1.21338

CivicScape

Article About CivicScape http://www.govtech.com/civic/Predictive-Policing-Startup-Publishes-Code-Online-Seeks-to-Address-Bias.html

CivicScape Source Code https://github.com/CivicScape/CivicScape

Notebooks for Testing CivicScape Predictions

I. Crime Data Validation Practices (R) https://github.com/CivicScape/CivicScape/blob/master/evaluation_notebooks/notebooks/DataInputsPractices.ipynb

II. Model Data Practices (Python) https://github.com/CivicScape/CivicScape/blob/master/evaluation_notebooks/notebooks/ModelDataPractices.ipynb

IV. Preventing and Diagnosing Bias in CivicScape https://github.com/CivicScape/CivicScape/blob/master/evaluation_notebooks/notebooks/PreventingBias.ipynb


Other Resources GitHub Repos About Algorithmic Fairness

Audit AI https://github.com/pymetrics/audit-ai

Fairness https://github.com/redshiftzero/fairness