Great Data Lake — Rent Demand Pressure Quantification Dataset
Built a real estate data product that equips developers, operators, and rehabbers with actionable insights into market demand and geographic preferences by...
Great Data Lake LLC ran from 2017 to 2022 as a data brokerage and value-add business I co-founded, focused on transforming large raw datasets into clean, compliant, commercially valuable data products. The company processed hundreds of terabytes of real-time data streams and sold subscription-based datasets serving defense, government, advertising, and finance clients using Spark, Databricks, AWS (S3, Redshift), and Redis.
GDL originally rented Lumate’s technology and IP to deliver curated subscription datasets, effectively transforming a once media-trading platform into a data brokerage engine. Products included location datasets, the Rent Demand Pressure Quantification dataset for real estate developers, and reseller channel integrations. The business model required understanding who needs what data, in what format, at what freshness, and under what compliance constraints—skills developed through years of Lumate’s adtech data infrastructure.
More context: greatdatalake.com
Demographic Prediction Model and Machine Learning Pipeline
Built predictive audience demographic datasets using graph databases and AI/ML. Trained models to predict demographic attributes of mobile device audiences...
Enhanced IP Geolocation Model for Security and Verification
Designed a novel IP geolocation confidence model combining location observation data with network topography analysis to improve the accuracy of geographic...
Great Data Lake LLC — Data Brokerage and Value-Add Business
Founded and ran a data brokerage from 2017 to 2022 that turned hundreds of terabytes of raw location and advertising data into clean, compliant, sellable datasets for defense, government, and finance customers.
Location Observation Fraud Outlier Identification
Used Tableau and sampled data to identify impossible or improbable movement patterns in location observation datasets, then designed a system to tag and filter...
Microservices Platform Modernization (EKS, ArgoCD, Helm)
Revised the 2014 container platform in 2018 onto EKS, ArgoCD, Helm, and GitHub Actions — moving from hand-run deployments to declarative, GitOps-driven delivery.
Scoring Algorithm for Customer Revisit Attribution
Designed, implemented, and tested 150 iterations of a scoring algorithm to determine the likelihood of a customer revisiting a physical store, based on mobile...
Voronoi Regions for International Geofencing
Created an algorithm to build an optimal international geofencing system for hundreds of millions of postal address regions, incorporating feedback from 32...