Stock Risk Analyzer

Stock Risk Analyzer is a powerful, machine learning-driven application designed to help investors, traders, and financial analysts assess stock market risk levels efficiently and accurately. By leveraging historical data and key technical indicators, this tool classifies stocks into risk categories (Low, Medium, High), empowering users to make informed investment decisions.

](https://www.python.org/downloads/) [ [](https://opensource.org/licenses/MIT)

Table of Contents

• Introduction
• Key Features
• Methodology
• Why This Project is Important
• Features
• Installation
• Usage
• Command-Line Interface (CLI)
• Web Application
• REST API
• Contributing
• License
• Acknowledgments
• Contributors
• Sponsor

Introduction

Stock Risk Analyzer is an open-source application designed to help investors, traders, and financial analysts assess the risk levels of stocks using machine learning techniques. By leveraging historical data and technical indicators, the application classifies stocks into risk categories (Low, Medium, High), providing users with valuable insights to make informed investment decisions.

Key Features

• 📊 Real-time stock data analysis
• 🤖 ML-based risk classification
• 📈 Technical indicator calculations
• 🌐 Web interface & REST API
• 📱 CLI support for automation

#### Features In Depth

• Machine Learning Classification:
• Uses LightGBM for fast and accurate risk predictions.
• Labels stocks as Low, Medium, or High risk.

• Real-Time Stock Data:
• Integrates with the Yahoo Finance API for fetching historical and current stock data.

• Technical Indicator Calculations:
• Computes key indicators such as Moving Averages (MA50, MA200), RSI, Volatility, and Bollinger Bands.

• User-Friendly Web Interface:
• Built with Flask, allowing users to analyze stocks through a simple browser interface.

• CLI Support:
• Analyze stocks programmatically via a command-line interface.

• Extensibility:
• Modular codebase allows easy integration of new features or additional data sources.

Methodology

The risk level is determined using the LightGBM Classifier with the following methodology:

1. 1.Risk Score Calculation ($\alpha$):

$$\alpha = w_1\sigma + w_2|R_t| + w_3\left|\frac{P_t - MA_{50}}{MA_{50}}\right| + w_4\left|\frac{P_t - MA_{200}}{MA_{200}}\right|$$

where $w_i$ are the learned weights

1. 1.Risk Categories:

• Low Risk: $\alpha where $\theta_1$ and $\theta_2$ are threshold values determined through model training

For more details, please see the PoC.md file.

Why This Project is Important