Sipaling is a web application that predicts stock prices using an LSTM deep learning model. It allows users to select a stock, specify a date range for historical data, and predict future prices for a specified number of days.
- Select stock codes and company names from a predefined list.
- Fetch historical stock data from Yahoo Finance.
- Predict stock prices using a pre-trained LSTM model.
- Visualize actual and predicted stock prices.
- Customizable forecast duration (1-100 days).
-
Clone the repository:
git clone https://github.com/ramadhanep/sipaling.git cd sipaling -
Install the required packages:
pip install -r requirements.txt
-
Download or place the pre-trained LSTM model (
stock_dl_model.h5) in the project directory. -
Ensure the
stock_codes.csvfile with stock codes and company names is present in the project directory.
-
Run the Streamlit app:
streamlit run app.py
-
Open your web browser and go to
http://localhost:8501. -
Use the sidebar to:
- Select a stock code and company name.
- Choose the start and end dates for historical data.
- Specify the number of days to forecast.
-
Click the "Prediksi" button to view the predictions.
app.py: The main application code.stock_dl_model.h5: Pre-trained LSTM model for stock price prediction.stock_codes.csv: CSV file containing stock codes and company names.requirements.txt: List of Python dependencies.
- pandas
- numpy
- datetime
- plotly
- yfinance
- tensorflow
- scikit-learn
- matplotlib
- streamlit
This project is licensed under the MIT License - see the LICENSE file for details.
- Yahoo Finance for providing historical stock data.
- Streamlit for providing an easy-to-use web application framework.
- TensorFlow for the deep learning framework used to build the LSTM model.
Contributions are welcome! Please create a pull request or submit an issue if you have any suggestions or improvements.