Welcome to our comprehensive AI-driven project focused on quantitative modeling for the stock market. This repository contains robust implementations of machine learning algorithms to build predictive models using stock price data (OHLC - Open, High, Low, Close).
The goal of this project is to design and implement machine learning models for stock price analysis and forecasting. By leveraging modern Python libraries and machine learning frameworks, we aim to generate actionable insights from complex market data.
Stock Data Processing: Efficient handling and transformation of OHLC data using our custom distribution class.
Machine Learning Models: Implementation of classification and regression models tailored to stock market trends.
Data Handling: Use of NumPy and Pandas for data wrangling.
Statistical Analysis: Insightful analysis using key statistical techniques.
Scalable Framework: Code structure designed for extensibility and scalability.
-- KNN -- RandomForest -- SVM
Prerequisites Ensure you have the following installed on your machine: Python 3.7+ NumPy Pandas scikit-learn
git clone https://github.com/Coderixc/AlgorithmAiMl.git cd AlgorithmAiMl
pip install -r requirements.txt
⚙️ Usage
Data Preparation: Ensure your stock data is in the data/ directory.
Model Training:
python src/ml_pipeline/train_model.py
Evaluation: Evaluate the model using test data and generate performance metrics.
The project implements the following models:
Linear Regression: For trend forecasting.
Random Forest: For robust predictions.
Support Vector Machines (SVM): For classification tasks.
Neural Networks: Leveraging feedforward architectures for complex data patterns.
🛡️ License
This project is licensed under the MIT License.
📬 Contact
For queries or suggestions, feel free to reach out at kchanchal78@gmail.com.