Skip to content
Providing the solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data.
Jupyter Notebook
Branch: master
Clone or download
Latest commit f1d729a Feb 14, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Data_Transformation remove Findal Code 3 Feb 6, 2017
Feature_Selection Graph Feb 6, 2017
Graph add some graph Feb 6, 2017
Model_Selection add graphs Feb 6, 2017
README.md Update README.md Feb 14, 2017

README.md

Modeling High-Frequency Limit Order Book Dynamics Using Machine Learning

  • Framework to capture the dynamics of high-frequency limit order books.

Overview

In this project I used machine learning methods to capture the high-frequency limit order book dynamics and simple trading strategy to get the P&L outcomes.

  • Feature Extractor

    • Rise Ratio

    • Depth Ratio

      [Note] : [Feature_Selection] (Feature_Selection)

  • Learning Model Trainer

    • RandomForestClassifier
    • ExtraTreesClassifier
    • AdaBoostClassifier
    • GradientBoostingClassifier
    • SVM
  • Use best model to predict next 10 seconds

  • Prediction outcome

  • Profit & Loss

    [Note] : [Model_Selection] (Model_Selection)

You can’t perform that action at this time.