Skip to content

Aakashdeep-Srivastava/Algorithmic-Trading-Model-for-BTC-USDT-Market

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Algorithmic Trading Model for BTC/USDT Market 📈

Welcome to our GitHub repository, where we're innovating the cryptocurrency trading space with our cutting-edge Algorithmic Trading Model focused on the BTC/USDT market. Dive into the world of machine learning, statistical modeling, and advanced programming to unlock new potentials in trading strategies. 🚀

📘 Introduction

  • Problem Statement: Exploring the significance of algorithmic trading models in the BTC/USDT cryptocurrency market.
  • Objective: Utilize machine learning, statistical modeling, and programming skills to pioneer ML-based algorithmic trading.

📝 Problem Description

  • Tasks: Data acquisition, preprocessing, model design, backtesting, risk management, and optimization with a spotlight on BTC/USDT market dynamics.

📊 Data and Resources

  • Historical Data: BTC/USDT trading pair data from January 1, 2018, to January 31, 2022.
  • Data Sources: Encouragement to utilize public cryptocurrency market data sources, API services, or simulated data for comprehensive analysis.

🛠 Methodology

Time Series Analysis

  • 📉 Trend Insights: Examination of BTC/USDT closing prices to decipher cryptocurrency trends.
  • 🔄 Lag Plots: Analysis of time series correlation with its lagged values to understand evolving patterns.

Preprocessing

  • 🔍 Stationarity Assessment: KPSS Test indicates non-stationarity, leading to preprocessing steps like differencing and log transformations for stabilization.

Models

  • Time Series Models: Application of moving averages for trend analysis and decision-making.
  • Machine Learning Models: Deployment of LSTM networks for capturing complex market dynamics.
  • Risk Management: Utilization of GARCH models for volatility assessment and management.

📚 Reference

  • "Bitcoin Return Volatility Forecasting: A Comparative Study between GARCH and RNN"

📝 Summary

  • Max Drawdown: 10%
  • Sharpe Ratio: 0.0017
  • Net Profit: Exceeding benchmark return of 0%
  • Risk-Reward Ratio: 1.01
  • Max Duration of Single Trade: 0.116 days

Feel free to explore our repository for more details on our models and methodologies. Your contributions and feedback are highly appreciated! 🌟


Happy Trading! 💼

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published