rough-volatility

A Python implementation of the rough Bergomi model.

C Bayer, B Stemper (2018). Deep calibration of rough stochastic volatility models.

C++ implementation of rBergomi model

Neural network framework for volatility surface approximation and calibration. Supports rough Heston/Bergomi, random grids, multi-regime architectures.

Bayer, Friz, Gulisashvili, Horvath, Stemper (2017). Short-time near-the-money skew in rough fractional volatility models.

Bayer, Friz, Gassiat, Martin, Stemper (2017). A regularity structure for finance.

Repository of the 'Pricing under Rough Volatility Models' Student Lab

Sixteen option pricers over six stochastic models including Heston, Bates, SABR and rough Bergomi, spanning analytic, lattice, finite-difference, COS Fourier and Monte Carlo methods.

Deep-learning option pricing and hedging: a neural surrogate for Asian options benchmarked against Monte Carlo, a rough Bergomi model for 0DTE, a CVaR deep hedging policy, live calibration, and an interactive dashboard.

Latent contagion, risk-neutral compression, and option-manifold pricing in Volterra-Perron rough markets.

A high performance pricing and calibration engine for Rough Volatility (rBergomi) models using a hybrid Python/C++ architecture with PyBind11.

Comparative analysis of Value at Risk (VaR) measures using Black-Scholes pricing under different volatility models: jump diffusion, SABR and rough volatility.

Derivatives pricing library: Black-Scholes-Merton (16 Greeks), Monte Carlo with variance reduction, Asian/Barrier/Lookback/Digital exotics, Heston (Fourier pricing, QE simulation, SPX calibration), rough Bergomi (hybrid scheme). 1,013 tests, QuantLib-validated, 97% coverage.

Numba-accelerated Rough Bergomi volatility model for derivatives pricing. Tested on Tesla (TSLA).

Regime-Aware Multi-Agent Portfolio Allocator — a five-phase ML pipeline combining HMM regime detection, LightGBM alpha generation, deep rough volatility calibration, and PPO reinforcement learning for dynamic asset allocation.

Organize fitness guidance and manage daily workout routines with this browser-based personal trainer application.

Pathwise conditional-density and Rao-Blackwellized calibration for local stochastic rough volatility

Generative model for rough volatility: log-signatures + a learned Besov-wavelet decoder reconstruct high-frequency texture via differentiable IDWT. Pluggable MLP/attention/transformer backbones, scale-weighted wavelet loss, and a 5-dataset multi-domain registry (fBM, rough Bergomi, Burgers turbulence, CHB-MIT EEG, ESC-50 audio).

Neural SDE framework for rough volatility modeling (H ≈ 0.1) with deep hedging. Implements Davies-Harte fBM, signature-based losses, and convergence analysis.