JonusNattapong/trading-lstm-xauusd

Trading LSTM Model for XAUUSD

This is a PyTorch LSTM model trained to predict price direction (up/down) for XAUUSD (Gold Futures).

Model Details

• Architecture: LSTM with 2 layers, 32 hidden units
• Input: 50 timesteps of 16 technical indicators
• Output: Probability of price going up (sigmoid)
• Training Data: XAUUSD historical data from 2010-2023
• Loss: Binary Cross Entropy
• Optimizer: Adam with L2 regularization

Features Used

• Close, Volume, RSI_14, SMA_5, SMA_20, EMA_5, EMA_20
• MACD, MACD_Signal, MACD_Diff
• BB_Upper, BB_Lower, BB_Middle
• ATR_14, OBV, ROC_12

Usage

import torch
from model import TradingLSTM

model = TradingLSTM()
model.load_state_dict(torch.load('trading_lstm.pth'))
model.eval()

# Prepare input sequence (50, 16)
# Predict probability of up move
prediction = model(sequence)

Disclaimer

This model is for educational purposes only. Trading involves risk.