Algorithmic trading has always fascinated me. Not just because of its potential to automate wealth creation, but because of the challenge of turning human intuition into a structured, data-driven system.
As a student at UC Berkeley studying Economics and Data Science, and someone with years of experience in manual stock trading, I’m now building my own algorithmic trading software. The system is based on breakout trading principles inspired by the Qullamaggie strategy, which identifies stocks that are starting to break through key resistance levels. These moments often capture the transition between hesitation and momentum — a point where opportunity forms.
Why This Project Matters
Manual trading taught me timing, patience, and the psychology behind every move. Algorithmic trading forces me to take that instinct and formalize it.
What drew me to this project: • The chance to combine finance, data, and software engineering in one system • The challenge of converting human recognition into quantitative logic • The goal of building something that can scale and operate independently
Current Focus
I’m currently developing the data collection pipeline using Python, Pandas, and yfinance. This foundation will handle the essentials: gathering, cleaning, and organizing price data for analysis and backtesting.
My main priorities right now: • Testing which APIs provide the best mix of speed, accuracy, and reliability • Structuring time-series data for efficient scanning and feature extraction • Preparing for a framework that can eventually support live breakout detection
Next Steps
Once the data layer is complete, I plan to develop: • A signal engine to identify potential breakout opportunities • A risk management module that handles stop-loss and position sizing • A backtesting system to evaluate performance over historical data
The goal is to take intuition and turn it into code. Every design choice should reflect a real-world trading principle.
What This Means to Me
This project isn’t just about automation or profit. It’s about building a system that reflects how I understand risk, opportunity, and decision-making. It’s about learning how human judgment can be distilled into logic that still adapts and improves over time.
If you’re interested in trading systems, market structure, or the connection between finance and computation, I’d be glad to connect and exchange ideas.