Fundamental package for quantitative finance with Python.
Project description
QuantFinLib
QuantFinLib is a comprehensive Python library designed for quantitative finance. It offers a wide range of tools and algorithms that cater to various domains within quantitative finance, including machine learning, asset management, portfolio optimization, time series transformations, indicators, labeling, feature engineering, stochastic simulation, randomization tests, and backtesting. This library aims to provide robust and efficient solutions for financial data analysis, modeling, and trading strategy development.
Time Series Simulation
Historical Sampling : Returns are randomly sampled from a historical time-series. The generated random simulation has the same return distribution as the historical return distribution, but any autocorrelation or dependencies over time is broken. This simulation method is used as a benchmark for generating time series that have no structural patterns, only random patterns.
Brownian Motion : Classical random price model without memory. Price changes are Normal distributed, the price can potentially go below zero.
Model | Properties |
---|---|
Historical Sampling | Returns have the same distributions as in the past |
Brownian Motion | Classical random price model without memory |
Geometric Brownian Motion | Classical random price model without memory, and where prices are postive |
Ornstein Uhlenbeck | Mean reverting model |
Garch | Dynamical volatility |
Dynamic Conditional Correlation GARCH | Dynamical volatility and correlations |
Markov Chains | Discrete state transitioning model |
Phase Randomisation | Randomization that preserves return distributions and autocorrelations |
Fractal Brownian Motion | Brownian motion with trends or mean reversion |
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for quantfinlib-0.0.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 825f1bbd33b9a373c29366716f9d1dbb11dccf878fa88f9689836280e97bff5a |
|
MD5 | 9341c478f8e52673e317e63d07cc736e |
|
BLAKE2b-256 | 8bf06f78803a07319223b597424baeac9c727a981075138a91d3abfe567d7109 |