Featured Project
Market Intelligence Platform
A full-stack equity research system covering 5,200 US stocks. Ingests daily market data and SEC filings, runs factor decomposition and anomaly detection, and surfaces trading signals through an interactive research dashboard — with no external server required at runtime.
5,200
US stocks tracked
4,800+
SEC filings classified
125
Industry clusters
20k+
Lines of code
Factor Decomposition
Market, sector, and cluster betas with leave-one-out regression to prevent self-reference bias. Orthogonalised factor returns and intra-cluster crowding signals.
Anomaly Detection
Rolling 125-day z-score analysis across volume and returns for all 5,200 tickers. Filterable by sector, cap tier, and z-score threshold.
SEC Filing Pipeline
Automated 10-K/20-F scraping with three-fallback extraction. 4,800+ companies classified into 15 sectors and 125 clusters using Claude AI.
AI Narrative Clustering
Claude-powered thematic clustering of market observations. Tracks how narratives form, evolve, and dissolve across the market over time.
Serverless Architecture
44MB data payload compressed to 8MB gzip. Self-contained HTML dashboard with no runtime server dependency — instant load, fully offline-capable.
End-to-End Pipeline
From raw API data to interactive dashboard: Polygon.io OHLCV ingestion, split adjustment, parquet storage, SQLite databases, and Python-to-JS compilation.