https://github.com/mohammad95labbaf/eurusd_lstm_attention
This project is dedicated to forecasting 1-hour EURUSD exchange rates through the strategic amalgamation of advanced deep learning techniques. The incorporation of key technical indicators—RSI, MA, EMA, and VWAP—enhances the model's grasp of market dynamics
https://github.com/mohammad95labbaf/eurusd_lstm_attention
attention attention-mechanism bilstm exponential-moving-average forecasting forex forex-prediction lstm lstm-cnn moving-average rsi technical-indicators time-series
Last synced: 5 days ago
JSON representation
This project is dedicated to forecasting 1-hour EURUSD exchange rates through the strategic amalgamation of advanced deep learning techniques. The incorporation of key technical indicators—RSI, MA, EMA, and VWAP—enhances the model's grasp of market dynamics
- Host: GitHub
- URL: https://github.com/mohammad95labbaf/eurusd_lstm_attention
- Owner: mohammad95labbaf
- Created: 2023-12-06T12:21:32.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-12T19:25:01.000Z (9 months ago)
- Last Synced: 2025-03-24T06:22:28.384Z (3 months ago)
- Topics: attention, attention-mechanism, bilstm, exponential-moving-average, forecasting, forex, forex-prediction, lstm, lstm-cnn, moving-average, rsi, technical-indicators, time-series
- Language: Jupyter Notebook
- Homepage:
- Size: 2.99 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# EURUSD_LSTM_Attention
## Overview
This project is dedicated to predicting 1-hour EURUSD exchange rates using a sophisticated combination of deep learning techniques. The process follows a systematic approach, starting with meticulous data preparation, including formatting and Min-Max scaling to ensure optimal model convergence. The incorporation of technical indicators such as RSI, MA, EMA, and VWAP enriches the model's understanding of market dynamics.
## Model Architecture
The heart of the predictive power lies in the model architecture, which seamlessly integrates LSTM cells, self-attention mechanisms, and 1D convolutional layers. This design is crafted to capture intricate temporal patterns in the EURUSD exchange rates. The implementation is carried out using TensorFlow, providing a customizable and flexible framework.
## Training and Evaluation
The training phase is marked by hyperparameter experimentation and continuous monitoring to ensure the model's effective learning. Evaluation metrics, including Mean Squared Error (MSE) and Mean Absolute Error (MAE), provide valuable insights into the model's performance.
## Deployment and Visualization
Once trained, the model is deployed to predict unseen data. Visualizations play a crucial role in analyzing performance patterns, aiding in the identification of strengths and areas for improvement. The insights gained from these visualizations guide further refinements in the model.
## Goal
Ultimately, this project aims to leverage the power of deep learning to gain nuanced insights into short-term EURUSD fluctuations within the dynamic financial landscape. Whether you're a financial analyst, trader, or enthusiast, this repository provides a comprehensive solution for predicting and understanding the ever-changing landscape of currency exchange rates.
Feel free to explore the code, dive into the details, and contribute to the ongoing refinement of this predictive model. Happy forecasting!
## How to Use
Certainly! Here's a more formal step-by-step guide on how to use the code with your `EURUSD_H1.csv` file in Google Colab:
---
### Project Usage Guide for Google Colab
#### 1. Upload Data to Google Colab
- Open [Google Colab](https://colab.research.google.com/).
- Create a new notebook or open an existing one.
- Use the following code to upload your CSV file:
```python
from google.colab import files
# Upload your CSV file
uploaded = files.upload()
```
Click on the "Choose Files" button, select your `EURUSD_H1.csv` file, and wait for the upload to complete.