From Full Transparency to Breakthrough Performance
You've identified your needs and want proven tools to multiply your AI capabilities. My two machine learning products span the full spectrum, from a fully transparent model you can read end to end to a breakthrough engine built for absolute predictive performance. Both rest on original mathematical research.
Sigma
- Instant learning on production data, with a conditional inference tree library in Python
- Full transparency and statistical rigor, with significance tests and confidence intervals at every step
- Production-ready and source-available, with minimal dependencies and a simple API
Tau
- Fully automated tabular learning engine, handing back a finished model out of the box
- Breakthrough accuracy, outperforming gradient boosting and tabular foundation models at every scale, from 30-record datasets to millions of records
- Handles messy, real-world data such as missing labels, random effects, and selection bias