Skip to main contentCrunch is not theoretical. It has been proven in some of the most demanding quantitative environments
on earth. We are now opening it up so anyone can use it to solve real-world problems.
Below are examples of use cases enabled by leveraging collective intelligence through the Crunch
protocol:
Finance
Cross-Sectional Asset Ranking
In collaboration with ADIA Lab, Crunch achieved a double-digit improvement
in cross-sectional asset ranking compared to the lab’s strongest internal models.
Structural Break Detection
In collaboration with ADIA Lab, Crunch detected structural breaks in the
market using models from the
Structural Break Crunch competition.
Mid-Market Pricing and Volatility Prediction
Mid+One™, a high-frequency mid-market pricing engine built on Crunch, is live and being tested by
major institutions for:
Science
Enabling Research on Autoimmune Diseases
In a competition organized by the Broad Institute of MIT and
Harvard, Crunch models outperformed internal benchmarks on biomedical vision tasks, demonstrating
that the network generalizes beyond finance.
Together with the Broad Institute of MIT and Harvard, we are
crowdsourcing new approaches in the
Obesity ML competition, where Crunchers
tackle obesity prediction using real-world data.
Crypto
Powering Bittensor Miners
A coordinator node powers miners on the
Synth Bittensor Subnet, enabling any machine learning engineer to
participate in the Synth subnet and furthering the reach of the Synth subnet.
