Forecasting implied volatility surface with generative diffusion models

By Chen Jin, Ankush Agarwal

Published 2026-05-11

Everscope rating

2039.8

Relevance to quantitative trading

9 / 10

Implementation complexity

8 / 10

Reproducibility

4 / 5

About this paper

Methodology: Conditional Denoising Diffusion Probabilistic Model (DDPM) with SNR-weighted arbitrage penalty. Problem types: Time Series Forecasting, Generative Modeling, Density Estimation, Risk Management, Portfolio Optimization.

arXiv:2511.07571 · Code · Paper rankings

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