Stock Price Prediction using Machine Learning

Overview

This project is in the early development stage. The aim is to explore and test various machine learning models for predicting stock prices. At this stage, the focus is primarily on evaluating different types of ML algorithms to identify which ones offer the most promise.

Getting Started

Prerequisites

Ensure you have the following installed:

• Python 3.9.19
• pip

Installation

1. Clone the repository:

   git clone [email protected]:alexobrads/algorithmic-trading-bot.git
   cd algorithmic-trading-bot
   

2. Install the required packages:

   pip install -r requirements.txt

Tested Models

We have explored and tested various machine learning models to evaluate their effectiveness in predicting stock prices, including:

1. Gaussian Processes:
   • A non-parametric approach widely used for regression tasks.
2. Long Short-Term Memory (LSTM):
   • A type of recurrent neural network (RNN) highly effective for time-series forecasting.
3. Neural Networks:
   • Various architectures of neural networks, including both shallow and deep networks, for regression and forecasting tasks.

Usage

Running Experiments

Use the Jupyter notebooks available in the notebooks directory to run different experiments. You can open the notebooks using:

jupyter notebook