← Home

Research & Writing

Technical writing, data analysis notebooks, and research on data science, machine learning, and system optimization.

On disabling ML in production

What I learned when my live trading system's ML ensemble silently degraded in production, and the disciplined reintroduction of machine learning that came after.

machine learningtrading financereal time systems

Atlas in production: putting a forecasting system in front of real capital

How the Atlas forecasting system handles 542,000 rows/second of market data with sub-second regime detection — async service architecture, dependency-ordered startup, and 10Hz health monitoring.

machine learningtrading financesystem optimization

How Atlas's database got 810× faster: a single-pattern fix

Atlas couldn't start. The trading system's database initialization was taking 6.6 seconds, blocking 37 features from loading. The fix was small.

database performancesystem optimizationtrading finance

Deploying ML in production: a working reference (Part 1)

Serving architectures, containerization, lifecycle management, performance optimization, drift detection, and monitoring — with benchmarks and code from production systems.

machine learningdevopspython

Database performance optimization: a reference (Part 1)

A working reference for production database tuning — SQLite PRAGMAs, schema, indexing, transactions, batching, pooling, and the monitoring that proves it's working.

database performancesystem optimizationpython

Database optimization: a working reference

Six database optimization techniques — predicate pushdown, row group pruning, result caching, async I/O, indexes, and where SIMD goes wrong — with impact numbers and code.

database performancesystem optimizationrust

Replacing DuckDB with Rust: 10.4× through predicate pushdown

I replaced DuckDB with a custom Rust query engine for a trading-system time-series workload. Five iterations, 10.4× speedup, one optimization that backfired.

database performancesystem optimizationrust

Cinestyle: matplotlib themes pulled from film

A small Python library of matplotlib themes — Film Noir, Ghibli, Wes Anderson, Blade Runner, Star Wars — applied to 50,000 IMDB reviews.

data visualizationpythonmatplotlib

ML deployment: a working reference for getting models into production

A field-tested reference for taking ML models from prototype to production — serving patterns, containerization, monitoring, drift detection, and the operational practices that make the difference.

machine learningdevopspython

WebAssembly visualization with Rust: when JavaScript runs out of room

Building browser-side data visualizations in Rust compiled to WebAssembly — particle systems, large-dataset rendering, and the practical wins over a pure-JS implementation.

data visualizationrusttypescript

A local-LLM scraper for Chamber of Commerce directories

Built a pipeline that extracts 296 businesses from Chamber of Commerce directories in 9 minutes using a local 7B-parameter model — 100% name/phone capture, no API costs.

data engineeringautomationnlp