Manifold is a visual debugging tool for machine learning developed by Uber. Machine learning is widely used across the Uber platform to support decision making and forecasting for features such as ETA prediction and fraud detection, the company explained.

The tool aims to help engineers and scientists identify performance issues across ML data slices and models, and diagnoses their root causes by surfacing feature distribution differences between subsets of data.

The first version includes model-agnostic support for general binary classifications and regression model debugging that allows users to analyze and compare models of various algorithm types. 

It also includes visualization support for tabular feature input including numerical, categorical, and geospatial feature types that helps users better understand the potential cause for certain performance issues. 

“Since highlighting this project on the Uber Eng Blog earlier this year, we have received a lot of feedback from the community regarding its potential in general purpose ML model debugging scenarios. In open-sourcing the standalone version of Manifold, we believe the tool will likewise benefit the ML community by providing interpretability and debuggability for ML workflows,” Uber wrote in a post.