Tools & Guides

The Data Science and Public Policy Team at Carnegie Mellon University creates and maintains a growing number of tools and guides to help improve the way people do data science for social impact. Our goal with these tools and guides is to help data scientists and government and nonprofit practitioners create impactful and equitable data science solutions to social problems. All of our tools and guides are born from our own experience working with government and nonprofit partners on data science projects that help them better serve their communities.

All of our tools and guides are regularly updated and open source. You can learn more about them below and by clicking links for more information about different tools and guides. We’re always open to suggestions about how to improve our tools and guides and resources that might benefit people doing data science for social good.


An open source machine learning toolkit to help data scientists, machine learning developers, and analysts quickly prototype, build and evaluate end-to-end predictive risk modeling systems for public policy and social good problems.

Learn More About Triage


An open source bias audit toolkit for machine learning developers, analysts, and  policymakers to audit machine learning models for discrimination and bias, and make informed and equitable decisions around developing and deploying predictive risk-assessment tools.

Learn More About Aequitas

Scoping Guide

A guide for scoping data science projects for social impact. This guide is intended for government and nonprofit practitioners, as well as data scientists and other data workers, and lays out the steps and considerations for building an impactful data science project. It is accompanied by a Scoping Worksheet that people can work through when planning a project.

Learn More About the Scoping Guide

Data Maturity Framework

A framework for assessing your organization’s readiness for a data science project. This framework walks government and nonprofit practitioners, as well as data professionals, through the organizational and data and technology requirements for a successful and impactful data science project. It is accompanied by a worksheet and a survey for assessing your organization’s readiness.

Learn More About the Data Maturity Framework

Legislative Influence Detector

This project provides tools to help analyze and access government bills. Using the Sunlight Foundation’s collection of state bills and model legislation scraped from lobbying groups from around the country, we built tools to shed light on the origination and diffusion of policy ideas around the country, the effectiveness of various lobbying organizations, and the democratic nature of individual bills, all in near real time.

Learn More About the Legislative Influence Detector