This project focuses on predicting the stock prices of Tesla (TSLA) and Apple (AAPL) using advanced machine learning techniques, specifically Liquid Neural Networks (LNN). The goal is to leverage historical stock data to forecast future prices with high accuracy.
yfinance
library, covering daily stock movements from specific start dates up to the present.The data for this project is retrieved from Yahoo Finance, focusing on the following stocks:
Features included are Open, High, Low, Close, Adjusted Close, and Volume. Technical indicators such as MACD, RSI, Bollinger Bands, and others are calculated to enhance the dataset.
To run this project on your local machine, follow these steps:
Clone the repository to your local machine:
git clone https://github.com/HusseinJammal/Liquid-Neural-Networks-in-Stock-Market-Prediction.git
cd /Liquid-Neural-Networks-in-Stock-Market-Prediction
Navigate to the project directory:
cd stocks
Install necessary dependencies:
npm i
Start the application:
npm run start
Run the Python application:
npm run app.py
Ensure you have Python and Node.js installed on your machine, along with necessary libraries such as yfinance
, numpy
, pandas
, sklearn
, and any specific libraries for LNN or deep learning frameworks you are using.
Detailed feature engineering steps include the creation of:
Utilization of LNN with configurations for different layers, including dropout and regularization to prevent overfitting.
The models are evaluated using the following metrics:
Results from these metrics provide insights into the models' predictive accuracy and performance.
Contributions to this project are welcome. Please fork the repository and submit pull requests with any enhancements or bug fixes.