I'm originally from Philadelphia, and graduated from Washington University in St. Louis in 2016 with degrees in Accounting and Sports Management. After graduation, I worked at Deloitte as a consultant in their tax practice, where the emergence (and value) of data analytics and predictive modeling quickly became clear. Because I most enjoyed my data-centric projects at Deloitte, I spent time learning programming languages R and Python, both in and out of the workplace, and utilized these languages to conduct a number of analyses surrounding the 2017 Major League Baseball season (see FanGraphs). The impetus behind joining the M.S. program at UNH was to expand my skills in coding and predictive analytics, while also having the freedom to pursue the independent projects which I find the most interesting.
Going forward, I hope to serve as a data scientist with a professional sports organization, consulting firm, or start-up. More important than the job's industry, however, is the opportunity to keep learning.
Thus far, the two most interesting projects I've worked on during the program have been related to the National Football League. One, entitled Assigning Success Likelihoods to Recently Drafted Quarterbacks, does just that - it utilizes random forest modeling to predict recent college quarterbacks' respective chances at success in the pros. The other, Which NFL Fanbase Had the Worst Week 1?, uses sentiment analysis to analyze thousands of online forum posts, ultimately determining which football team's week 1 performance elicited the most positivity and negativity from its fanbase. Through each project, I have further developed my skills in machine learning, web scraping, and data cleaning, as well as communicating my findings in a clear and concise manner.
Feel free to click the links above or visit saisenberg.com to learn more about each project.
What have you found valuable about the M.S. program thus far?
The professors in the M.S. program are incredibly supportive and engaging. They are always eager to sit down and discuss any questions I come across in my projects, and are thoroughly invested in the success of myself and other students in the program. When teaching a particularly difficult concept or machine learning tool, they are not satisfied with simply explaining what that tool is, but ensure that we understand the theory behind the concept itself.
Connect with Sam on LinkedIn