Traditionally, volatility is modeled using parametric models. This project focuses on predicting EUR/USD volatility using more flexible, machine-learning methods.

Estimation of realized quantities

R code and Realized Volatility (RV) series set for fitting NN-based-HAR models to multinational RV series.

Intraday volatility estimation using High-Frequency Financial Data

Official code - M2VN(Multi-Modal Learning Network for Volatility Forecasting)

Compare realized volatility estimators for intraday data

Utilities for fetching, reading, validating, caching, consolidating, and splicing intraday OHLCV price files from multiple vendors.

Replication of "Variance Risk Premia in the Interest Rate Swap market" paper (2016) by Desi Volker PhD

Implied volatility surface fitting, SVI calibration, variance swap pricing, arbitrage detection, and greeks surfaces in Python. Uses the FlashAlpha API.

R package to estimate and forecast the HAR (Heterogeneous Autoregressive) model and its extensions.

Forecasting realized volatility for 5 US sector ETFs using statistical models (ARIMA, GARCH, EGARCH), machine learning (Ridge, XGBoost, SVR), and deep learning (LSTM) on 20 years of daily data.

Tick-by-tick futures microstructure engine.

Calculation of stock realized variance based on trade data on WRDS cloud

Dynamic Delta-Hedging Strategy on Real Market Data (NVDA).Dynamic Delta-Hedging Strategy on Real Market Data (NVDA). Analysis of the impact of volatility estimators (Garman-Klass vs Close-to-Close) on the performance of a self-financing replicating portfolio

Transformer for FX realized-volatility forecasting. Each hourly block encodes the joint market state (10 forex pairs + 14 macros + events + HAR features) into a single context vector; 24-horizon output for one target symbol.

C++17 realised-volatility forecasting pipeline: Bloomberg BLPAPI → SQLite → feature engineering → Chronos-2 inference via ONNX Runtime, benchmarked against HAR-RV and persistence with Diebold-Mariano tests.

High-frequency financial time-series toolkit: tick/volume/dollar bars, realized-volatility estimators, microstructure and order-flow metrics in Python

Realized volatility analytics dashboard for financial market analysis using Python and Streamlit.

HAR-RS-DOW variance forecasting for BTC-EUR with Value-at-Risk, Expected Shortfall (Basel III), option pricing, and live trading deployment on Bitvavo.

Chronos-2 foundation model significantly outperforms HAR at forecasting gold realised volatility — 30yr Bloomberg data, DM p<0.0001