Quantitative Equity Screener & Risk Management Architecture
Rule-based screening pipeline combining SEC balance sheet data and technical regime filters for US equities. Not financial advice.
Project Architecture & Case Study
The Challenge & Scope
Manually filtering thousands of publicly traded companies for both fundamental balance-sheet growth and technical momentum is intractable, often leading to unhedged volatility without systematic risk rules.
Technical Architecture & Solution
Built a multi-tiered Python analytical engine: SEC EDGAR balance sheet and revenue growth extraction, Weinstein Stage 2 technical filters, and market sentiment inputs. Engineered market regime filters (200 SMA), trailing stop logic, and a deterministic backtesting simulation harness.
Results & Key Deliverables
Constructed a functional quantitative data pipeline that automates equity screening and simulates disciplined risk-management rules on historical data.
About the Project
A quantitative software engineering exploration analyzing quarterly corporate filings (SEC EDGAR) and trend regime indicators across US equity markets (S&P 500 and Nasdaq). Tests asymmetric risk heuristics, trailing stop mechanics, and regime filters within an automated backtesting architecture. Strictly educational software engineering; does not constitute investment advice.
Architected, designed, and engineered entirely by Ahmet Mert Yiğitbaşı.
Technologies
- Python 3.10
- Pandas & NumPy
- SEC EDGAR Data Pipeline
- Quantitative Backtesting Engine
- Risk Management Heuristics