ML-fairness-gym: A Tool for Exploring Long-Term Impacts of Machine Learning Systems - Deepstash

Bite-sized knowledge

to upgrade

your career

Ideas from books, articles & podcasts.

created 8 ideas


ML-fairness-gym: A Tool for Exploring Long-Term Impacts of Machine Learning Systems

ML-fairness-gym: A Tool for Exploring Long-Term Impacts of Machine Learning Systems


85 reads

Common methods for assessing the fairness of machine learning systems involve evaluating disparities in error metrics on static datasets for various inputs to the system.

Indeed, many existing ML fairness toolkits (e.g., AIF360, fairlearn, fairness-indicators, fairness-comparison) provide...

There are cases (e.g., systems with active data collection or significant feedback loops) where the context in which the algorithm operates is critical for understanding its impact. In these cases, the fairness of algorithmic decisions ideally would be analyzed with greater consideration...

In order to facilitate algorithmic development with this broader context, we have released ML-fairness-gym, a set of components for building simple simulations that explore potential long-run impacts of deploying machine learning-based decis...

A standard practice in machine learning to assess the impact of a scenario like the lending problem is to reserve a portion of the data as a “test set”, and use that to calculate relevan...

The ML-fairness-gym simulates sequential decision making using Open AI’s Gym framework. In this framework, agents interact with simulated environments in a loop. At each step, an agent chooses an action that then affects the environ...

Since Liu et al.’s original formulation of the lending problem examined only the short-term consequences of the bank’s policies — including short-term profit-maximizing policies (called the max reward agent) and policies subject to an equality of opportunity (EO) constraint — we use the ML-fairne...

Our long-term analysis found two results. First, as found by Liu et al., the equal opportunity agent (EO agent) overlends to the disadvantaged group (group 2, which initially has a lower average credit score) by sometimes applying a lower threshold for the group than would be app...

Our paper extends the analysis of two other scenarios that have been previously studied in the academic ML fairness literature. The ML-fairness-gym framework is also flexible enough...

1 Reaction



created 3 ideas

one sided and annoyingly incorrect copy, at least the list of protocols is of the big players



193 reads

It's time to




Jump-start your

reading habits

, gather your



remember what you read

and stay ahead of the crowd!

Takes just 5 minutes a day.


+2M Installs

4.7 App Score