COMPANY: CODTECH IT SOLUTIONS
NAME: Syed Mujtaba Siraj Uddin
NCS ID: E19E86-0116588288923
DOMAIN: Artificial Intelligence
DURATION: 4 WEEKS
MENTOR: Vaishali
This project focuses on building an intelligent model capable of predicting future stock prices based on historical financial data. The system utilizes machine learning techniques such as Linear Regression, and can be extended with LSTM neural networks for time-series forecasting.
The goal is to enable investors, analysts, and students to understand how data-driven models can forecast market trends and stock movements based on previous performance.
The project also demonstrates how real-world data preprocessing, model training, and prediction can be implemented and visualized interactively in a Jupyter Notebook.
Historical stock price data is fetched from Yahoo Finance using the yfinance library.
The dataset includes features like Open, Close, High, Low, and Volume.
Handle missing values.
Convert the ‘Date’ column into a proper datetime format.
Split the data into training and testing sets.
Implemented a Linear Regression model using scikit-learn.
Train the model on historical closing prices to predict future values.
Predict future stock prices.
Evaluate using R² score and Mean Squared Error (MSE).
Visualize results using matplotlib.
Integrate with Gradio to allow users to input stock symbols (e.g., “AAPL”, “GOOG”) and visualize predicted prices.
Python
Scikit-learn
Pandas
NumPy
Matplotlib / Seaborn
yFinance
Gradio
Predicted vs Actual stock prices plotted on a graph. Model performance metrics (R², MSE). Interactive input/output interface (optional).
