[!IMPORTANT]

### 🤝🏻 Special Acknowledgement

Special thanks to Hasan Rizvi and Mega Satish for their meaningful contributions, guidance, and support that helped shape this work.

Overview

This project investigates the application of K-Means Clustering on financial market data. By categorizing stocks into distinct clusters based on their historical price movements, the system provides a data-driven approach to understanding market dynamics and constructing balanced investment portfolios.

Developed as a mini-project for the Big Data Analytics & Computational Lab - I curriculum, this implementation showcases the full data science pipeline: from data acquisition via Yahoo Finance to feature engineering (volatility/returns) and unsupervised model validation.

Resources

| # | Resource | Description | |---|---|---| | 1 | Project Model | Complete Jupyter Notebook implementation | | 2 | Technical Specification | Technical Architecture & Specification | | 3 | Technical Report | Comprehensive project documentation | | 4 | Technical Presentation | Visual overview of methodology and results | | 5 | Project Demo | Real-time demonstration of the analysis |

[!TIP]

Cluster Validation Best Practices

Use the Elbow Method to identify the optimal number of clusters by plotting Within-Cluster Sum of Squares (WCSS). Complement this with the Silhouette Score to validate cluster cohesion and separation for robust market segmentation.

Features

| Feature | Description | |---------|-------------| | K-Means Clustering | Unsupervised segmentation of stocks based on volatility and returns metrics. | | Data Acquisition | Automated historical data retrieval via Yahoo Finance API (yfinance). | | Feature Engineering | Calculation of annualized volatility and returns for each stock. | | Cluster Validation | Elbow Method and Silhouette Score for optimal cluster determination. | | Visualization | Interactive scatter plots and cluster centroid analysis. | | Portfolio Optimization | Data-driven insights for diversified investment strategies. |

Tech Stack

• Language: Python 3.8+
• ML Framework: Scikit-Learn (K-Means, Silhouette Analysis)
• Data Processing: Pandas, NumPy
• Visualization: Matplotlib, Seaborn
• Data Source: yfinance (Yahoo Finance API)

Project Structure

OPTIMIZING-STOCK-TRADING-STRATEGY-WITH-K-MEANS-CLUSTERING/
│
├── docs/                                          # Formal Documentation
│   └── SPECIFICATION.md                           # Technical Architecture & Specification
│
├── Mega/                                          # Archival Attribution Assets
│   ├── Filly.jpg                                  # Companion (Filly)
│   ├── Mega.png                                   # Author Profile Image (Mega Satish)
│ ├── Mini-Project/                                  # Research & Academic Assets │   ├── BDAMINI-PROJECTPPT...pdf                 # Project Presentation (PDF) │   ├── BDAMINI-PROJECTPPT...pptx                # Project Presentation (PPTX) │   ├── BDAMINI-PROJECTREPORT...docx             # Technical Project Report (DOCX) │   └── BDAMINI-PROJECTREPORT...pdf              # Technical Project Report (PDF) │ ├── Source Code/                                   # Model Implementation │   ├── OPTIMIZING STOCK TRADING STRATEGY...ipynb  # Core K-Means Analysis Notebook │   └── StockMarketClustering.py                 # Production-ready Python Script │ ├── .gitattributes                                 # Global Git LFS & Config │   └── .gitignore                                 # Asset Exclusion Manifest ├── requirements.txt                               # Dependency Manifest ├── CITATION.cff                                   # Scholarly Citation Metadata ├── codemeta.json                                  # Software Metadata Manifest ├── LICENSE                                        # MIT License Terms ├── README.md                                      # Comprehensive Archival Entrance └── SECURITY.md                                    # Vulnerability Exposure Policy

Quick Start

1. Prerequisites

• Python: Version 3.8 or higher.
• Hardware: 4GB Minimum RAM (8GB recommended for large datasets).
• Environment: Virtual environment (venv) is highly recommended.

[!WARNING]

Technical Dependencies & Data Variability

This system is built using Python 3.8+ and Scikit-Learn. Stock market data is inherently volatile; results may vary based on the date range and ticker symbols selected. For stable execution and reproducible analysis, it is recommended to run this in an isolated virtual environment.

2. Setup & Deployment

• Clone the Repository:

git clone https://github.com/Amey-Thakur/OPTIMIZING-STOCK-TRADING-STRATEGY-WITH-K-MEANS-CLUSTERING.git
    cd OPTIMIZING-STOCK-TRADING-STRATEGY-WITH-K-MEANS-CLUSTERING

• Install Dependencies:

pip install -r requirements.txt

3. Launch Application

• Run the Python Script:

cd "Source Code"
    python StockMarketClustering.py

• Explore the Notebook:

[!TIP]

Optimizing Stock Trading Strategy with K-Means Clustering

Experience a high-fidelity interactive simulation grouping major S&P 500 companies based on volatility and return patterns to identify optimal trading opportunities through unsupervised machine learning and advanced market segmentation.

Launch Interactive Notebook

Recent enhancements also include a Reinforcement Learning (RL) gateway for advanced strategy optimization.

Launch Stock Trading RL Web App

Usage Guidelines

This repository is openly shared to support learning and knowledge exchange across the academic community.

For Students Use this project as a reference for understanding clustering algorithms, financial data preprocessing, and the application of Big Data Analytics in stock market optimization.

For Educators This project may serve as a practical example or supplementary teaching resource for Big Data Analytics (CSDLO7032) and Computational Laboratory–I (CSL704) modules. Attribution is appreciated when utilizing content.

For Researchers The implementation provides a foundation for exploring more advanced clustering techniques (e.g., DBSCAN, Hierarchical Clustering) and sentiment-integrated market analysis.

License

This repository and all linked academic content are made available under the MIT License. See the LICENSE file for complete terms.

[!NOTE]

Summary: You are free to share and adapt this content for any purpose, even commercially, as long as you provide appropriate attribution to the original author.

Copyright © 2022 Amey Thakur, Hasan Rizvi, Mega Satish

About This Repository

Created & Maintained by: Amey Thakur, Hasan Rizvi & Mega Satish Academic Journey: Bachelor of Engineering in Computer Engineering (2018-2022) Institution: Terna Engineering College, Navi Mumbai University: University of Mumbai

This project features the Optimizing Stock Trading Strategy with K-Means Clustering, an analytical utility developed as a 7th Semester Mini-Project. It explores the application of unsupervised machine learning for financial market analysis and portfolio optimization.

Connect: GitHub  ·  LinkedIn  ·  ORCID

Acknowledgments

Grateful acknowledgment to Hasan Rizvi and Mega Satish for their exceptional collaboration and scholarly partnership during the development of this project. Their technical expertise, constant support, and dedication to software quality were instrumental in achieving the project's analytical objectives. Learning alongside them was a transformative experience; their thoughtful approach to problem-solving and encouragement turned complex challenges into meaningful learning moments. This work reflects the growth and insights gained from our side-by-side academic journey. Thank you, Hasan and Mega, for everything you shared and taught along the way.

Grateful acknowledgment to the faculty members of the Department of Computer Engineering at Terna Engineering College for their guidance and instruction in Big Data Analytics. Their expertise in data science and machine learning helped shape the technical foundation of this project.

Special thanks to the mentors and peers whose encouragement, discussions, and support contributed meaningfully to this learning experience.