All Projects → BlackArbsCEO → Mixture_model_trading_public

BlackArbsCEO / Mixture_model_trading_public

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Mixture model trading public

Research
Notebooks based on financial machine learning.
Stars: ✭ 714 (+330.12%)
Mutual labels:  jupyter-notebook, trading, finance, algorithmic-trading
trading-rules-using-machine-learning
A financial trading method using machine learning.
Stars: ✭ 16 (-90.36%)
Mutual labels:  finance, trading, algorithmic-trading
piker
#nontina, #paperhands,, #pwnzebotz, #tradezbyguille
Stars: ✭ 63 (-62.05%)
Mutual labels:  finance, trading, algorithmic-trading
Alphalens
Performance analysis of predictive (alpha) stock factors
Stars: ✭ 2,130 (+1183.13%)
Mutual labels:  jupyter-notebook, finance, algorithmic-trading
portfoliolab
PortfolioLab is a python library that enables traders to take advantage of the latest portfolio optimisation algorithms used by professionals in the industry.
Stars: ✭ 104 (-37.35%)
Mutual labels:  finance, trading, algorithmic-trading
AutoTrader
A Python-based development platform for automated trading systems - from backtesting to optimisation to livetrading.
Stars: ✭ 227 (+36.75%)
Mutual labels:  finance, trading, algorithmic-trading
Quantdom
Python-based framework for backtesting trading strategies & analyzing financial markets [GUI ]
Stars: ✭ 449 (+170.48%)
Mutual labels:  trading, finance, algorithmic-trading
Sequence-to-Sequence-Learning-of-Financial-Time-Series-in-Algorithmic-Trading
My bachelor's thesis—analyzing the application of LSTM-based RNNs on financial markets. 🤓
Stars: ✭ 64 (-61.45%)
Mutual labels:  finance, trading, algorithmic-trading
Sgx Full Orderbook Tick Data Trading Strategy
Providing the solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data.
Stars: ✭ 733 (+341.57%)
Mutual labels:  jupyter-notebook, trading, algorithmic-trading
Algorithmictrading
This repository contains three ways to obtain arbitrage which are Dual Listing, Options and Statistical Arbitrage. These are projects in collaboration with Optiver and have been peer-reviewed by staff members of Optiver.
Stars: ✭ 157 (-5.42%)
Mutual labels:  jupyter-notebook, finance, algorithmic-trading
Mlfinlab
MlFinLab helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.
Stars: ✭ 2,676 (+1512.05%)
Mutual labels:  trading, finance, algorithmic-trading
Turingtrader
The Open-Source Backtesting Engine/ Market Simulator by Bertram Solutions.
Stars: ✭ 132 (-20.48%)
Mutual labels:  trading, finance, algorithmic-trading
Machine Learning For Trading
Code for Machine Learning for Algorithmic Trading, 2nd edition.
Stars: ✭ 4,979 (+2899.4%)
Mutual labels:  jupyter-notebook, trading, finance
Introneuralnetworks
Introducing neural networks to predict stock prices
Stars: ✭ 486 (+192.77%)
Mutual labels:  trading, finance, algorithmic-trading
Pandas Ta
Technical Analysis Indicators - Pandas TA is an easy to use Python 3 Pandas Extension with 130+ Indicators
Stars: ✭ 962 (+479.52%)
Mutual labels:  jupyter-notebook, trading, finance
Pyportfolioopt
Financial portfolio optimisation in python, including classical efficient frontier, Black-Litterman, Hierarchical Risk Parity
Stars: ✭ 2,502 (+1407.23%)
Mutual labels:  jupyter-notebook, finance, algorithmic-trading
Finrl Library
FinRL: Financial Reinforcement Learning Framework. Please star. 🔥
Stars: ✭ 3,037 (+1729.52%)
Mutual labels:  jupyter-notebook, finance
Python For Data Science
A blog for data analytics using data science technologies
Stars: ✭ 139 (-16.27%)
Mutual labels:  jupyter-notebook, finance
Grademark
An API for backtesting trading strategies in JavaScript and TypeScript.
Stars: ✭ 140 (-15.66%)
Mutual labels:  trading, algorithmic-trading
Interactivebrokers Algo System
Java/MySQL live algorithmic trading using Interactive Brokers API
Stars: ✭ 151 (-9.04%)
Mutual labels:  trading, finance

README

Note: If you have issues viewing the notebooks copy/paste the nb link into nbviewer.jupyter.org

What is this repository for?

The primary goal of this repo is to demonstrate the workflow between research of a quantitative idea or theory to implementation as a potential live trading strategy. Unlike other finance based tutorials the results will not be cherry picked to show only the best of the best examples. Sometimes results are counterintuitive, sometimes they are conflicting. Real strategy development is often dirty, complex, full of starts and stops and requires us to use all of our skills to extract the signal from the noise. With that said I welcome interactive engagement, ideas, insight, and constructive criticism, especially if errors or bugs are found. (IN-PROGESS...)

The strategy development focuses on using mixture models as a method for market timing. Types of mixtures to be covered include:

  • gaussian mixtures (in-progress...)
  • bayesian mixtures (not-started)
  • nonparametric mixtures (not-started)
  • gaussian processes (not-started)

There are some challenges to implementation

  • This repo will attempt to make use of the QuantConnect platform. It is built in C# with python integrated as a first class citizen on the platform. However, for those of us who are migrating to this platform from Quantopian, there is a non-trivial learning curve.
  • The python infrastructure is more flexible i.e. there are less restrictions on packages and which classes can be imported, there are more securities available for testing and trading.
  • The python infrastructure is more immature however i.e. there is no interactive debugger (as of Dec. 11, 2017), the error stack traces are not as informative and do not point to which lines caused particular errors, so testing can be a pain.
  • The owner of the platform Jared Broad is very responsive and the team is active in communicating with the users and working with us to improve the platform

Chapter (Notebook) Outlines

  1. Motivation: (Completed-Editing...)
    • this chapter goes through a demo of challenges to time series prediction using real market data
    • what is stationarity?
    • why one distribution isn't enough?
    • how can multiple distributions help?
  2. Gaussian mixtures: (Completed-Editing...)
    • In this chapter we explore the underlying intuition behind gaussian mixtures
    • We will construct a simple implementation of the expectation-maximization algorithm
    • We apply a gaussian mixture model to predict an asset's return distribution using sklearn
  3. Designing the strategy: (Completed-Editing...)
    • In this chapter we will use what we have learned to construct a strategy idea
    • We rapidly prototype the idea using the data we have to decide if the idea is worth further testing
  4. Implementation: (Completed-Editing...)
    • In this chapter we will implement the idea into a strategy using the Quantconnect platform IDE.
    • We will implement the simplified components of an automated strategy including:
      • slippage/fees
      • order management,
      • inventory management,
      • indicator construction,
      • task scheduling
  5. Evaluation: (Completed-Editing...)
    • Backtest the strategy.
    • Download backtest portfolio equity quantconnect algo equit download
    • Read in Algorithm Portfolio Equity
    • Choose the Best Algorithm Among 4 Variants
    • Choose Best Bayesian Model of Algorithm Returns
    • Compare Bayesian Cones for all Algos and all Return Models
    • Compare Best Algo Predicted Portfolio Ending Values
    • Compare Best Algo Predicted CAGR Distributions
    • Model Averaging

QuantConnect Links/Resources for Python Users

Who do I talk to about this repo?

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].