I am currently Researcher at the American Institutes for Research focusing on data mining and machine learning for science and innovation policy. My primary interests are unstructured data including text as well as prediction models. I have experience with text mining and computational linguistics including data collection (web scraping, pdf), data organization (MySQL, Python objects, matching and disambiguation algorithms), and data analysis and modeling (LDA/topic modeling, information retrieval, Random Forests, bibliometrics, Social Network Analysis). I also have skills of web development (especially with Python-based frameworks, e.g. Django, Flask).