End-to-End Parametric Portfolio Policies for Cross-Asset Futures Timing: When Do AI Models Beat Simple Rules?

By Austin Pollok, Kevin Robik

Published 2026-07-01

Everscope rating

1921.7

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

3 / 5

About this paper

Methodology: End-to-End Parametric Portfolio Policy with Differentiable Sharpe Ratio. Problem types: Portfolio Optimization, Optimization, Reinforcement Learning, Risk Management.

arXiv:2607.00475 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.