The Financial Data Analytics Platform leverages data science and machine learning to analyze sectoral financial trends using data from the SEC EDGAR database. This project demonstrates how to transform raw financial data into actionable insights for stakeholders such as investors, policymakers, and business leaders.
- Advanced Data Processing: Automates data curation and storage using Python and MongoDB.
- Interactive Dashboards: Visualizes insights with Tableau, highlighting trends, profitability, and risks.
- Machine Learning Models: Implements predictive analysis to forecast market trends and evaluate company performance.
- Summarization with LLMs: Uses OpenAI GPT models for summarizing complex 10-K filings.
- Analyze financial data trends across sectors (e.g., Technology, Finance, Healthcare).
- Identify correlations between profitability, risk, and research investments.
- Present insights through interactive visualizations and dashboards.
- SEC EDGAR Database: Financial filings of publicly traded U.S. companies.
- Programming Languages: Python
- Database: MongoDB
- Visualization: Tableau
- Libraries: pandas, BeautifulSoup, LangChain
- APIs: SEC EDGAR API
- Machine Learning: Random Forest, Statistical Testing
-
Clone the repository:
git clone https://github.com/madhurlak0810/SEC-edgar.git
-
Install dependencies:
pip install -r requirements.txt
-
Setup MongoDB and OpenAI credentials
-
Go through qualitative analysis and Project checkpoint:
-
Visualize the insights with Tableau or view pre-generated dashboards using the tbwx file and excel.
- Madhur Lakshmanan: Data curation, preprocessing, and MongoDB integration and OpenAI integration and Github Pages implementation.
- Inesh Tandon: Machine learning model design and performance validation.
- Rohan Jain: Visualization and result analysis.
- Balamurugan: Visualization and documentation.
- Abhyansh Anand: Report creation and sectoral analysis.
GitHub Repository: SEC-edgar
For questions or suggestions, please contact Madhur Lakshmanan.