This study tackled a major healthcare challenge: identifying the over 200 million people worldwide who suffer from long COVID, a condition where symptoms persist long after the initial infection. Currently, doctors rely mainly on hospital records to identify these patients, but this approach misses many cases. The research team improved an existing computer prediction system by feeding it additional information beyond just medical records—including genetic data, lifestyle surveys, and activity data from fitness trackers like Fitbits. By combining these different types of information, their enhanced system became significantly better at correctly identifying who has long COVID and who doesn’t, improving accuracy from about 72% to 86%. Most importantly, the improved system was much better at avoiding false alarms—correctly ruling out people who don’t have long COVID 87% of the time compared to 70% with the original system. This advancement could help doctors more accurately screen patients for long COVID, leading to earlier diagnosis and treatment for millions of people who might otherwise go unrecognized and untreated.

Stanford GSB Professor Jung Ho Choi and Utah Professor Sara Malik approached my team, Data, Analytics, and Research Computing (DARC), to work with Glassdoor to acquire five data pillars for this research paper. It became abundantly clear that Glassdoor wasn’t willing to work with academia, so I built several webscrapes that collected employee reviews and salary compensation data at scale. Acknowledgment cited on the introductory page.

View the publication.

I was asked by Stanford Univesity Professor Rebecca Lester to build a Tableau based tool that would aggregate Opportunity Zones, which were defined in the “Tax Cuts and Jobs Act” of 2017. Challenges with this project were mainly around the limitations of Tableau not supporting U.S. Census tract data. Using python, I developed a polygon shapefile of all U.S. Census Tracts, a shapefile representing nearly seven million data points. After getting Tableau to construct the track polygons, I easily overlay the Opportunity Zone information into an interactive map.

Working alongside the Sustainable Energy Initiative at Stanford University’s Graduate School of Business, my task was to develop an online application that would serve not only Stanford University but also the public at large. Dealing with the nuances of a confidential data backend, coupled with the need to have a responsive web-tool, created several challenges with this project, all of which were exciting to overcome. Today three European universities and several universities in the United States are actively utilizing this tool.

I developed a tool for Professor Glenn Carroll, at Stanford University’s Graduate School of Business, that will allow him to evaluate organizational cultural heterogeneity. The Venn diagram tool I developed is a client-side tool written in Javascript, jQuery, AJAX, D3, HTML, and CSS. The tool ingests an excel file with unlimited columns (sets) and nearly instantaneously renders a Venn diagram based on the three sets with the highest means. The second section allows users to choose the three sets they wish to execute manually.

This paper, written by Bumpus and Comello and published on Nature.com, discusses Emerging clean energy technology investment trends. My contribution was cleansing, massaging, and developing data analysis to support Bumpus and Comello’s argument. I utilized Matlab, Tableau, and python extensively for this project. Credited for work in acknowledgments.

View the publication.

My contribution to this report/publication was the development of intuitive and concise data visualizations; visualizations that highlighted Latino entrepreneurs’ narrative. I leveraged Tableau and Python to create the visualizations while utilizing various data sources, including the U.S. Census report and Qualtrics surveys. View the publication.

View the publication.