Skip to content

This repository implements an SARIMAX model for predicting financial instrument prices (stocks, currencies, cryptocurrencies). The model uses gradient boosting to capture complex price patterns and handle diverse dataset characteristics for accurate price forecasting.

License

Notifications You must be signed in to change notification settings

taleblou/SARIMAX-Price-Prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SARIMAX Model for Financial Predictions

This repository contains an implementation of an SARIMAX model, specifically designed for predicting the prices of financial instruments such as currencies, stocks, and cryptocurrencies. The SARIMAX algorithm leverages gradient boosting techniques, enabling it to capture intricate patterns in price movements and handle various dataset characteristics effectively. This approach enhances the accuracy and robustness of price forecasts across various datasets.

This is the original code sample for the SARIMAX model. Explore my GitHub repository for additional models and implementations that cater to different financial prediction needs.

Performance Metrics

BTC-USD (Bitcoin)

Metric Open High Low Close
Mean Squared Error 0.001329 0.001132 0.001433 0.001341
Mean Absolute Error 0.027770 0.024768 0.029749 0.027989
R-squared 0.9402 0.9505 0.9374 0.9416
Median Absolute Error 0.022065 0.018228 0.023956 0.023222
Explained Variance Score 0.9415 0.9518 0.9387 0.9429

GC=F (Gold Futures)

Metric Open High Low Close
Mean Squared Error 0.001230 0.001201 0.001107 0.001179
Mean Absolute Error 0.028485 0.027900 0.027078 0.027747
R-squared 0.9396 0.9403 0.9458 0.9416
Median Absolute Error 0.027555 0.024508 0.024117 0.024435
Explained Variance Score 0.9414 0.9419 0.9475 0.9431

EURUSD (Euro/US Dollar)

Metric Open High Low Close
Mean Squared Error 0.000652 0.000609 0.000570 0.000652
Mean Absolute Error 0.020571 0.019287 0.018602 0.020559
R-squared 0.8512 0.8642 0.8727 0.8512
Median Absolute Error 0.017362 0.015519 0.015648 0.017201
Explained Variance Score 0.8520 0.8650 0.8735 0.8521

GSPC (S&P 500 Index)

Metric Open High Low Close
Mean Squared Error 0.000847 0.000731 0.000878 0.000921
Mean Absolute Error 0.021426 0.019786 0.021931 0.022897
R-squared 0.9375 0.9486 0.9352 0.9354
Median Absolute Error 0.017253 0.015680 0.017230 0.017625
Explained Variance Score 0.9392 0.9502 0.9368 0.9371

 

Related Websites

Free AI-powered short-term (5/10/30 days) and long-term (6 months/1/2 years) forecasts for cryptocurrencies, stocks, ETFs, currencies, indices, and mutual funds.

Get free trading signals generated by advanced AI models. Enhance your trading strategy with accurate, real-time market predictions powered by AI.

Discover free trading signals powered by expert technical analysis. Boost your forex, stock, and crypto trading strategy with real-time market insights.

About This Project

This SARIMAX model is an initial implementation, released for public use. The project demonstrates the potential of deep learning models for financial predictions. While this repository focuses on SARIMAX, I have also utilized other models, the code for which is available on my GitHub[https://github.com/taleblou/].

How to Use

  1. Clone this repository.
  2. Install the required libraries: pip install -r requirements.txt
  3. Prepare your dataset and follow the instructions in the notebook or script.
  4. Run the model and evaluate its performance using the provided metrics.

License

This project is open-source and available for public use under the MIT License. Contributions and feedback are welcome!

About

This repository implements an SARIMAX model for predicting financial instrument prices (stocks, currencies, cryptocurrencies). The model uses gradient boosting to capture complex price patterns and handle diverse dataset characteristics for accurate price forecasting.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages