FairLens unveiled: discover and measure data bias

The open-source Python library is instantly accessible and available on GitHub. Try FairLens in your workflow, and help develop new features to tackle fairness in machine learning and algorithmic bias.

FairLens open-source Python library

A robust bias and fairness toolset to incorporate into your own development environment.

Bias measurement

Measure the extent and significance of biases in datasets using a wide range of metrics

Sensitive attribute and proxy detection

Automatically identify and flag sensitive columns and hidden correlations between columns to protect sensitive attributes

Fairness scoring

Highlight hidden biases and correlations within a dataset by selecting a target variable

Reporting

Generate reporting on all detected biases and correlations within the dataset

Visualization tools

Visualize the distribution of a variable with respect to different sensitive demographics, or a correlation heatmap
CALLING ALL DEVELOPERS!

Contribute to FairLens

We open-sourced our statistical framework to identify and measure bias. Join us in making FairLens even more useful and increase the types of bias detected.
You can join us and help with:
Creating heatmaps between sensitive and non-sensitive columns
Confidence intervals for metrics
Reporting generation in the fairness scorer
Detecting sensitive attributes using word vectors
Adding public datasets

Learn more about AI
and data bias

Fairness and algorithmic biases in machine learning and recommendations to enterprise
AI meets the law: bias, fairness, privacy, and regulation
Synthetic data in machine learning: what, why, how?