This article lists some high-frequency quantitative trading code projects, most of which are from Github;
Including basic tutorials of mathematics/measurement/statistics/algorithms, order book analysis and market making strategies, traditional technical analysis, machine learning, deep learning, reinforcement learning and other categories;
All languages used are Python/Jupiter Notebook;
Basic Tutorial
https://github.com/crflynn/stoc hastic _
The realization of common random processes, including continuous, discrete, diffusion process, noise and other categories;
https://github.com/jwergieluk/o u_noise _
Generation, testing and parameter estimation of OU processes;
https://github.com/stmorse/hawkes _ _
Regarding the generation and parameter estimation of univariate and multivariate Hawkes process, the MAP EM algorithm is used for parameter estimation;
https://github.com/AileenNielse n/ TimeSeriesAnalysisWithPython
Basic time series tutorial, including reading time series data, decomposition of trend components and seasonal components, spectral analysis, clustering, etc.;
https://github.com/yangwohenmai _
Advanced time series tutorials, including time series forecasting based on statistics, LSTM, and deep learning;
https://github.com/youngyangyan g04/ leetcode -master
The problem-solving strategy of data structure and algorithm is continuously updated;
https://github.com/dummydoo/Advanced-Algorithmic-Trading _ _
The code implementation of the book “Advanced Algorithmic Trading”, the language used is python/R;
https://github.com/bukosabino _
The project homepage of an Affirm algorithm engineer is rich in content, including TA library implementation, time series prediction, feature engineering selection, etc., mainly in the field of machine learning;
Order Book Analysis and Market Making Strategies
https://github.com/nicolezattar in/ LOB -feature-analysis
Perform feature engineering analysis of limit order books, including the distribution of order sizes, order imbalances for price forecasting, probability of informed trading, volatility, and more. The author’s documentation and code are concise and clear, including some original literature;
https://github.com/ghgr/HFT_Bit coin _
Data analysis of the BTC order book and some examples of traditional high-frequency strategies;
https://github.com/yudai-il/High-Frequency _ _
Based on the research of level-2 limit order book and tick transaction data, the market expansion of order imbalance and buying and selling pressure is investigated;
https://github.com/jeremymck/High-Frequency-Data—Limit-Order-Books _ _
This project includes descriptive analysis of high frequency data, generation and parameter estimation of Hawkes process and simulation of limit order books;
https://github.com/Macosh/Order_Book _ _
An order book simulator, which realizes the functions of creating different types of orders, order matching, simulation generation, and database storage of historical orders;
https://github.com/fedecaccia/a vellaneda -stoikov
Implementation of Avellaneda-Stoikov market making algorithm;
https://github.com/mdibo/Avella neda -Stoikov
Another implementation version of the Avellaneda-Stoikov market making algorithm, which is more concise than the former;
https://github.com/jshellen/HFT _
Using the stochastic optimal control method to solve the AS market making algorithm and its variants, including the solver of the HJB equation and the output frame of the AS market making strategy;
https://github.com/huangzz119/O ptimalExecution_stochastic_control _
This project implements the optimal execution of the VWAP algorithm proposed by Frei, C. and N. Westray (2015). Optimal execution of a vwap order: a stochastic control approach. Mathematical Finance 25(3), 612–639. The project Including data process, parameter calibration, inventory change trajectory, etc.;
https://github.com/kousik97/Order-Execution-Strategy _ _
The realization of three optimal order execution strategies, in addition to the realization of the market shock function under the Almgren-Chriss framework;
contain original documents;
https://github.com/mmargenot/ma chine -learning-market-maker
Implementation of the article “Intelligent Market-Making in Artificial Financial Market”, a market-making strategy model based on Bayesian estimation;
https://github.com/armoreal/hft _
The high-frequency trading strategy tested the fitting of the Hidden Markov Model (HMM) and the OU process to the limit order book data; in addition, several typical high-frequency factors were also tested;
Traditional technical analysis, hedging
https://gitee.com/xuezhihuan/my-over-sea-cloud/tree/master/quantitative_research_report _ _
The recurrence of some brokerage research reports;
https://github.com/eyeseaevan/b itmex -algo
Trading strategy based on 1-minute trading data of ETH/USDT and XBT/USDT on BitMEX platform, using traditional technical analysis indicators for trading;
https://github.com/Davarco/Algo Bot _
An automated trading robot using mean reversion or trend following strategies;
https://github.com/JunqiLin/High-Frequency-of-BTC-strategy _ _
BTC high-frequency hedging strategy across exchanges;
https://github.com/rlindland/options-market-making _ _
Trading robots based on options market, including market making, statistical arbitrage, delta and vega hedging, etc.;
https://github.com/Harvey-Sun/W orld_Quant_Alphas _
Calculation and strategy of World Quant 101 alphas;
machine learning
https://github.com/rorysroes/SG X-Full- OrderBook -Tick-Data-Trading-Strategy
A quantitative strategy that uses machine learning methods to dynamically model limit order books, including data acquisition, feature selection, and model selection, which can be used as the baseline for machine learning strategies;
deep learning
https://blog.csdn.net/bit452/ca tegory_10569531.html _
The code corresponding to the “Pytorch Deep Learning Practice” course is a good introduction to deep learning;
https://github.com/nicodjimenez/lstm _ _
A simple implementation of LSTM;
https://github.com/rune-l/HighF requency _
The neural network method is used to predict the price jump at the micro level, and the project integrity is relatively high.
https://github.com/umeshpalai/A lgorithmicTrading -MachineLearning
Use RNN, LSTM, GRU to predict stock price changes;
reinforcement learning
https://github.com/BGasperov/dr lformm _
The code implementation of “Deep Reinforcement Learning for Market Making Under a Hawkes Process-Based Limit Order Book Model”, a deep reinforcement learning market making strategy based on Hawkes process;
https://github.com/lucasrea/alg orithmicTrader _
A project that uses reinforcement learning for algorithmic trading;
https://github.com/gucciwang/mo neyMaker _
An algorithmic trading strategy based on reinforcement learning;
https://github.com/TikhonJelvis/RL-book _ _
The corresponding code implementation of the book “Foundations of Reinforcement Learning with Applications in Finance”;
https://github.com/mfrdixon/dq-MM _ _
Deep Q-Learning is used for market making and relies on the open source project Trading Gym;
————————————————————————————————————
PS: optional search keywords
bitcoin strategy
order book
market microstructure
crypto
Source: Zhihu www.zhihu.com
Author: Flying Sand Wind Transit
[Zhihu Daily] The choice of tens of millions of users, to be a big cow to share new things in the circle of friends.
click to download
This article is reproduced from: http://zhuanlan.zhihu.com/p/558902211?utm_campaign=rss&utm_medium=rss&utm_source=rss&utm_content=title
This site is for inclusion only, and the copyright belongs to the original author.