I'm a modeler, with a PhD in Machine learning. I worked at top labs (U. of Colorado, Boulder; Carnegie Mellon); But my speciality is to find and optimize business value. If you have a process that generates value (for example a page that sells something) I will tweak so it makes the most possible.|
I have two areas of expertise: Predictive analytics and semantic modeling.
(1) Predictive analytics, particularly customer lifetime value (CLV).
Customer Lifefitime Value (CLV) is the mythical 'magic number', the amount of money a particular customer will ever bring in. Knowing your CLV makes it trivial to:
- optimize marketing spend for different inbound channels.
- identify your highest value customers,
- identify those in danger of never coming back.
Most shops have a 'gut feeling' of what their CLV is, but no way of knowing for sure. Yet this is the number that would make the largest impact to their bottom line, if only it was possible to have it. Ah! Predicting the future is hard, right?
It turns out CLV can be computed with surprising accuracy (around 10% error) at the individual level. I use sophisticated bayesian models to estimate CLV. I look beyond what has happened in the past (which you get with say google analytics). CLV changes often, due to your marketing actions, season, or changes in the market. I retrain your models weekly to reflect those changes, and then suggest the actions that would make the largest impact (email campaigns, popups with offers triggered by user behavior on your site, etc).
(2) Statistical semantics, similarity, recommendations, algorithms that work at large-scale datasets (i.e., the entire semantic web). I've worked on semantics for the last 12 years.
Specialities: Creating and managing technical teams, git, python, R. Statistical semantics. Predictive modeling, Customer Lifetime Value (CLV). Conversion optimization, AB testing. Database marketing.