Aerosolve

A machine learning package built for humans.

Example: Neighborhood polygons based on listing density in San Francisco, generated using a multi-scale Kd-tree model.

Sophisticated ML Features

Aerosolve provides sophisticated machine learning features, such as geo-based features, controllable quantization and feature interaction. Provide human intuition to machine models by specifying prior beliefs.

Human Friendly, Debuggable Models

Aerosolve was designed to make feature engineering fast and painless. A feature transform language gives the developer full control over the features. General additive models provide lots of capacity while enabling easy interpretation.

Built on the JVM

Easily integrate with JVM projects. Aerosolve utilizes Scala for feature training, and provides a lightweight Java API for run time inference.