This repository showcases a stock price prediction project for 'Iran Kh. Inv.' using Gradient Boosting Regressor, along with the incorporation of technical indicators. The project aims to forecast future stock prices based on historical data and analyze the model's accuracy using Mean Squared Error, Mean Absolute Error, and R-squared Score. Stock Price Prediction with Gradient Boosting Regressor License
To get started with the project, follow these steps:
Clone the repository to your local machine:
git clone https://github.com/yourusername/stock-price-prediction.git
Install the required dependencies:
pip install pandas numpy matplotlib scikit-learn
The project consists of the following main components:
The historical stock data is stored in a CSV file (Iran Kh. Inv..csv). Data preprocessing steps, including data cleaning and scaling, are performed before training the model.
The Gradient Boosting Regressor model is initialized and trained on the preprocessed data to predict stock prices.
Model performance is evaluated using Mean Squared Error, Mean Absolute Error, and R-squared Score.
The stock data used in this project is sourced from the tsetmc database and is stored in a CSV file (Iran Kh. Inv..csv). The data includes historical stock prices and date information.
The stock price prediction model is built using the Gradient Boosting Regressor from scikit-learn. The model is trained on the preprocessed data to learn patterns and trends in stock prices.
The project includes visualizations of the actual stock prices and the corresponding predicted prices using matplotlib. These visualizations help in understanding the model's predictive capabilities.