About me

Resume

I’ve been working in data science since 2014 and exploring the stories in data my entire career. I began as a student of comparative literature and history, exploring compositional techniques and how they track onto larger trends in their physical and intellectual environment.

An interest in measurement and evaluation led me to public health at Johns Hopkins, where I studied how the environment influences mental and physical health. I carried out investigations of food environments and evaluated interventions to promote healthy behavior.

I found exploring invention impact really interesting and pursued my PhD in Policy Analysis at the RAND Corporation. While at RAND, I worked on projects evaluating infrastructure policies and workplace health programs.

At RAND, I began to explore datasets outside of those designed for the studies I was conducting (i.e. “real world” evidence). I began using social media data to investigate public discussion of health and voter file data to score individual likelihood to vote. I found the wealth of data and open source technologies enabled deeper exploration and produced more engaging data products.

Since then, I’ve explored big questions like which restaurants are the most risky, what people want to know about their local businesses and how to estimate customer budget from spend data.

Throughout my career, I’ve participated in the community by hosting speakers and workshops on open source topics, engaging in civic technology projects and sharing my expertise in the area of Natural Language Processing.

I tend to subscribe to the DJ Patil adage “move purposefully and fix things”. I’ve built and led data science teams and helped others build out their capacity and scope their projects. My experience has taught me that the most impactful data products are the ones that build on existing capacity. In my view, no solution can be implemented without buy-in and no buy-in can be achieved without communication and trust.

I’m always open to hearing about interesting projects, speaking opportunities and ideas.

Close Window

Forecasting and prediction

I have worked on predictive modelling with limited data resources (crash prediction from public data), rare outcomes (website visitor conversion) and uncertain targets (marketing budget forecasting). My experience gives me an edge when it comes to building predictive data products.

Close Window

Policy analysis

I obtained my PhD from the RAND Corporation while working on projects related to health, infrastructure and public policy. I am formally trained in econometrics and have applied these methods to assess health programs and risk.

Close Window

Text analytics

I have extensive experience leveraging text data in analytics products for academic research, marketing and risk assessment. I have also given talks and taught courses on the subject.

Close Window

Training/Mentoring

I find sharing my experience with others to be extremely rewarding. I have constructed and taught courses and workshops throughout my career and provided mentorship to coworkers and the community.

Close Window

Building Data Science capacity

I have built three data science teams from the ground up and have worked as a consultant helping companies build and scope their data science practice. These groups continue to deliver impact and expand on the structure that we founded.

Close Window

Community contributions

I maintain a close engagement with the tech community by organizing meetups, contributing to social good projects and regularly posting projects and interesting material to my blog.

Close Window