volatility-modeling

OIPD computes the probabilities of an asset's future price as implied by the options market.

GARCH and Multivariate LSTM forecasting models for Bitcoin realized volatility with potential applications in crypto options trading, hedging, portfolio management, and risk management

Fourier-transform pricing, Monte Carlo validation, and calibration of European options under stochastic-volatility models in Python

A vectorized implementation of py_vollib, that supports numpy arrays and pandas Series and DataFrames.

Curso diseñado para proporcionar una comprensión muy profunda del Trading Cuantitativo, fusionando los principios de Ingeniería Financiera con el poder de la Inteligencia Artificial, todo implementado en Python. Desarrollarás algoritmos y estrategias avanzadas que aprovechan datos financieros y técnicas de Inteligencia Artificial.

Market Data & Derivatives Pricing Tutorial based on Jupyter notebooks

A package for online distributional learning.

Machine learning for financial risk management

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

Implementation with a Jupyter Notebook of the VIX index modelization provided in its CBOE white paper.

SABR Implied volatility asymptotics

"Modeling Volatility and Risk Spillover Between the Financial Markets of US and China Using GARCH Value-at-Risk Forecasting and Granger Causality" — Undergraduate thesis, Seoul National University Dept. of Economics

A practical introduction to derivatives pricing and risk : 10 Jupyter notebooks from 17 years on trading desks.

C++ option pricing library on vanillas & exotics, Python volatility calibration library

Implementation of option pricing models using Numba that performs better. This entire project has utilized as little libraries as possible, even though certain models have their own Machine Learning Model with assessment and performance.

Python wrappers around QuantLib and Pandas to easily generate volatility surfaces

Measure market risk by CAViaR model

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

Collection of numerical methods for high frequency data, in Python notebooks