Production-Ready Statistical Arbitrage Engine
In-progress market data + cointegration control plane I'm hardening for pilots
Media & Demos
Asset Correlation Heatmap
Price & Spread Analytics
Role
Founder / Quant Developer
Period
2025 – Present
Category
trading
Overview
An in-progress quantitative trading system I am actively dogfooding for systematic pair trading. It already ingests market data, runs cointegration analytics, and renders dashboards, but it is still under development while I refine the control plane and risk tooling before inviting anyone else in.
Key Highlights
- Pair discovery with Spearman/Pearson correlation and Engle–Granger cointegration
- Robust multi-provider data pipelines with Redis caching and automated backfills
- Z-score driven backtesting with risk metrics and performance analytics
- Production dashboard with correlation heatmaps and live trade monitoring
- Full observability with Prometheus metrics and health checks
Tech Stack
Summary
On-page overviewThis is a concise summary of the challenges, solution, and outcome for this project. Use the Case Study button above for the full deep dive.
The Problem
I needed a trustworthy statistical arbitrage stack for my own research before ever pitching it to clients, but off-the-shelf tools could not keep up with the cointegration + audit requirements I had in mind.
The Solution
The FastAPI services, data pipelines, and React dashboards are in place, and I am layering on an AI-powered audit subsystem so every ingest run narrates anomalies and suggested remediations while I iterate.
The Outcome
Today it powers only my workflows—no outside users yet—while I work toward a private beta once reliability, coverage, and governance are truly battle tested.
Team & Role
Still a solo build. My near-term focus is to harden the pipelines, add embeddings-driven monitoring, and push it toward the 'invincible' standard I aim for.
What I Learned
This project deepened my understanding of Python and FastAPI and reinforced best practices in system design and scalability. I gained valuable insights into production-grade development and performance optimization.