Powerful quantitative forecasting models.
Historically, quantitative models are domain-specific. Brilliant people spend their best years testing features, tuning hyperparameters, and iterating architectures within a narrow domain.
But scale is the panacea: large models will find patterns people, and specialized models, could not. Forecasting generalizes.
Automating Iteration
LLMs embedded in optimization loops, evaluated against fixed policies, can automate the build-test-improve modeling cycle. Think AlphaEvolve for forecasting problems.
Sample-Efficient General Models
Unlike existing forecasting models, our models leverage data from across contexts, and rely less on human intuition. And compared to LLMs, our models are built with more inductive priors and rely more heavily on inference-time compute, improving sample efficiency.
Why It Matters
We trade using our models and capital in the financial markets.
Our models could also be useful for forecasting supply chain volatility, energy demand, even earthquake risk.
Science is, Ian Hacking writes, the taming of chance. It is the process of iteratively updating priors. Better forecasting improves our ability to select interesting experiments (roughly those with greatest expected uncertainty reduction) and update priors.
Backed by YC & others
or email founders@zoaresearch.com