I love working with data. I spend my days deep in client data, running anything from ad hoc reports and analyses on the most recent table updates, to months long deep-dives iteratively building and testing models for customer behavior, anomaly detection, and other areas. After hours, I meet up with colleagues and friends, and put our data skills to work for non-profit groups and civic organizations, helping them analyze surveys, client information and more.
Coming from an academic research background rich in a variety of approaches for generating, analyzing, and modeling data, I have the skills to learn a new topic quickly and find the best approach to solving a problem. I’ve found that early, thorough research can save a huge amount of time on the back-end.
From years spent excelling at universities doing advanced technical research, to more recently innovating approaches to anomaly detection on large volumes of data, I have been thinking about approaches to analytics for my entire career.
I’m driven by trying to squeeze maximal understanding and insight from new datasets, new approaches and new software. I enjoy arguing about how best to answer a question, but I like, even more, to be proven wrong through a thorough analysis of the data.
When I’m not in front of a computer doing some data cleaning, model building, or coding, I’m usually found outside, cross-country skiing, playing ultimate frisbee or road cycling with friends.
MapReduce, Tableau, Cloudera Hadoop: Hue, Hive, Pig, Impala, Spark
R, Python, SAS, Matlab, C, ImageJ, Labview, Fourier processing, 3d modeling, Eigen analysis,
Python, NLP, nltk, automated summarization, regex, sentence tokenizing, named entity recognition
Scrapy, API queries, web crawling, xpath