Predictive Modeling, Data Mining, Web Analytics, Statistical Consulting, Artificial Intelligence, Other
Freelance computer scientist. From a disciplinary standpoint, I work in the areas of information retrieval, machine learning, computational linguistics, and applied statistics. From a task standpoint, I've worked on retrieval, categorization, clustering, filtering, routing, mining, extraction, authorship attribution, parsing, and pretty much anything else you can do to textual or partially textual data. Industries I've consulted to include web search, computational advertising, information security, data mining, venture capital, biotech, defense, nonprofits, government, and a range of startup companies.
The past few years, I've gotten particularly involved in work related to the law, both as a consulting expert on patent cases, and through a variety of electronic discovery activities. I am one of the founders of the TREC Legal Track, and created the first large scale public test collection for experimentation on e-discovery. I've consulted on e-discovery to both industry and law firms, designed machine learning algorithms for an e-discovery service provider, and developed training materials on e-discovery for a Fortune 100 company.