Scaling Laws for Market Prediction
How model capacity, data diversity, and compute interact when forecasting high-frequency and medium-horizon returns.
Related reports →Insights from the lab — technical notes on foundation models for markets, adaptive execution, and the limits of predictability.
Peer-reviewed thinking and technical notes on foundation models for markets, reinforcement learning in execution, and the human edge in AI-driven systems.
How model capacity, data diversity, and compute interact when forecasting high-frequency and medium-horizon returns.
Related reports →A framework for learning execution policies that remain robust under regime shifts and changing liquidity conditions.
Algorithmic proposals →Why research taste, hypothesis generation, and scientific skepticism remain decisive even as models grow more capable.
Frontier projects →