In action

Pilosa was first used to power lightning fast segmentation queries from a massive, disparate data set. Along the way we realized its implications far exceeded our initial use case.

Download our whitepaper
abstract logo

Chemical Similarity and the Tanimoto Algorithm


Chemical similarity is essential to pharmaceutical development. Running Tanimoto algorithms over Pilosa clusters allows researchers to conduct exhaustive searches of existing structures to identify target chemicals, accelerating drug development.

abstract logo

Monitoring Network Traffic

Network Security

Modern network attacks require an increasingly complex infrastructure of intrusion prevention, creating datastores which grow exponentially. Layering Pilosa atop existing security solutions allows us to analyze high-volume network data and even predict network intrusions.

abstract logo

Taming Transportation Data

Smart Cities

Transportation systems are vital to economic networks but produce massive amounts of data that are difficult to analyze. Using New York City taxi data, we harnessed Pilosa's ability to work across datastores while supporting granular attributes.

abstract logo

Understanding Fans at Umbel

Audience Segmentation

Umbel is where Pilosa’s journey began. See how the Umbel platform uses Pilosa to create highly-specific customer segments, allowing clients to personalize their messaging and increase revenue with data-driven, targeted campaigns.

abstract logo

Retail Analytics and the Star Schema Benchmark

Retail Analytics

Retail transactions produce huge volumes of data, and only fast queries can pull value out this mess of data. We used Pilosa to explore the well-known Star Schema Benchmark, producing impressive performance numbers in the process.