New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Jump to bottom

LSTM model with Optuna hyperparameter optimization for stock price prediction #9

Open

DarthCoder501 wants to merge 2 commits into GeomScale:main from DarthCoder501:main

DarthCoder501 commented Mar 23, 2025

This code introduces an LSTM-based model for stock price prediction, enhanced with Optuna hyperparameter optimization. The code includes:

Data preprocessing with new features like 7-Day SMA, 14-Day EMA, MACD, Stochastic Oscillator, and ATR to capture market trends and volatility.
Model architecture with LSTM layers, dropout for overfitting prevention, and Adam optimizer with MSE loss.
Hyperparameter optimization using Optuna to fine-tune:

Number of LSTM units
Dropout rate
Learning rate
Batch size
Number of epochs

Evaluation using metrics like MAE, MAPE, MSE, and RMSE, comparing non-optimized and optimized models.

DarthCoder501 added 2 commits

March 22, 2025 23:35


          Create LSTM.py

39068ab


          Update lstm.py

9130de9

# for free to join this conversation on GitHub. Already have an account? # to comment

Labels

None yet