I am a government professional with over a decade of data product consultant, leadership, project management, editing/writing and patent examination experience. I graduated in May 2018 with a Master’s of Science in Data Science from Indiana University. This blog covers a wide range of data topics presented with a non-technical audience in mind.
Laura H. Kahn
Indiana University, M.S. Data Science, January 2016 – May 2018
North Carolina State University, B.S. Textile Engineering and B.A. Spanish, August 1999 – May 2004
Universidad de Santander – Study Abroad for Spanish Language, September – December 2003
Universidad Technológica del Perú – Study Abroad for Spanish Language, June – August 2001
United States Patent and Trademark Office, Office of the Chief Information Officer (2007 – present)
Created user stories, implemented system requirements, and collaborated with developers to create Patent Examination Data System and Bulk Data Storage Systems in support of open government initiatives. Expert in extracting statistical knowledge and insight from databases with minimal supervision to support decision makers.
United States Patent and Trademark Office, Patents Technology Center 3700 (2004-2007)
Conducted technology research for biomedical patent applications and communicated patentability findings to customers.
Indiana University (2016-2018)
Data science project experience in graduate program including Data Acquisition, Data Mining, Data Cleaning, exploratory Data Analysis, Statistics, Data Manipulation, Machine Learning, Feature Selection, Data Visualization and Storytelling, Network Theory.
- Use of Artificial Neural Networks to Predict Poverty Indicators
Used multilayer perceptron neural networks to select most important features in household survey data sets; Log loss results in top 25% of crowdsourced World Bank data competition. Data-driven focus on social development topics.
- Algorithmic Trading of Coffee Futures with Machine Learning
Predicted daily coffee futures closing prices with Decision Tree Regression and Ridge Regression algorithms with a maximum percent prediction error of 0.00328.
- Morning Joe: Visualizing Coffee Rust, Production and Futures
Quantified and visualized the correlation between coffee rust, weather variables, production and futures prices in Brasil, Colombia and Papua New Guinea using regression techniques.
- Show me the Money: Forecasting Economic Aid with Machine Learning
Predicted USAID economic aid disbursements with support vector machine, decision tree, Naive Bayes and k-NN machine learning classifiers with accuracies averaging 91.86%; Poster presented at 2017 Jupyter Conference.
- Spatiotemporal Twitter Analysis of the Venezuelan Food Crisis
Quantified social reactions for 1.32 million Tweets from Caracas with accuracy improvement of up to 21%; Paper to be presented at 2018 SMAP Conference.
Energy Use in the Middle East
Data munging, interpretation and visualization of energy consumption.
Kahn, Laura H. “Spatiotemporal twitter analysis of the Venezuelan food crisis.” Journal of Food Processing Technology, 8:5. (2017): 51. Proceedings from the 2nd International Conference on Food Security and Sustainability. https://www.omicsonline.org/conference-proceedings/2157-7110-C1-062-011.pdf
The findings, interpretations and conclusions expressed herein are those of the author. All content provided on this blog is for informational purposes only.
The author does not make representations as to the completeness of any information on this site or found by following any link on this site. The author will not be liable for any errors or omissions in this information nor for the availability of this information.
Many of the links on this blog will take you to sites operated by third parties. The author does not endorse these sites, their opinions, or any products they may offer. These third party links are offered to stimulate discussion and thinking on topics related to open governance, including, transparency, accountability, citizen participation and technology and innovation.
All of the content on this blog is intended for the personal, non-commercial use of our users.