Welcome to the Stock Price Prediction repository! This repository contains code for predicting stock prices using two different techniques: Long Short-Term Memory (LSTM) neural networks and Linear Regression.
- data/
- TATA STEEL.csv
- resources/
- feature selection.pdf
- Stock-Market-Prediction-Using-LSTM-Recurrent-Neural-Network.pdf
- LSTM.ipynb
- Linear_reg.ipynb
The LSTM.ipynb Jupyter Notebook includes code for predicting stock prices using LSTM neural networks. It performs the following steps:
- Data loading and preprocessing.
- Scaling the data using Min-Max scaling.
- Creating training and testing datasets.
- Building an LSTM model.
- Training the model.
- Making predictions on the test data.
- Visualizing the predictions.
- Install the required libraries.
- Ensure you have access to the dataset at the specified URL.
- Run the code cells in this notebook to perform stock price prediction.
- Python
- pandas
- numpy
- scikit-learn
- keras
- tensorflow
- matplotlib
- Inspiration from Stock-Market-Prediction-Using-LSTM-Recurrent-Neural-Network.pdf.
- Feature selection techniques outlined in feature selection.pdf.
The Linear_reg.ipynb Jupyter Notebook includes code for predicting stock prices using Linear Regression. It performs the following steps:
- Data loading and preprocessing.
- Feature scaling using Min-Max scaling.
- Shuffling and splitting the dataset into training and testing sets.
- Building a Linear Regression model.
- Training the model.
- Making predictions on the test data.
- Calculating and displaying prediction error.
- Install the required libraries.
- Ensure you have access to the dataset at the specified URL.
- Run the code cells in this notebook to perform stock price prediction.
- Python
- pandas
- numpy
- scikit-learn
- matplotlib
- Feature selection techniques outlined in feature selection.pdf.
- Dataset used for prediction: TATA-STEEL.csv.
Feel free to contact me with any questions or suggestions related to this repository.
Happy coding!