Welcome to my site! My name is John Schwenck and I am an aspiring statistician with an adventurous spirit trying to change the world one iteration at a time. I am interested the general domain of machine learning, but specifically in computationally-intensive areas such as functional data analysis, dimensionality reduction, spatial interaction networks, quantile-based methods, and natural language processing (NLP). I find enjoyment in applying these methodologies to professional endeavors such as commodity market predictions, reservoir charicterization, and biostatistical applications, but also on a leisurely level with Poker and sports analytics.
Professional Experience
I am currently a Machine Learning Engineer at Wells Fargo in the Artificial Intelligence / Machine Learning Consumer Model Development Center (CMDC) where I work on devloping and deploying various quantitative models at scale using various big data frameworks such as Spark and Hadoop using a wide variety of programming languages and computational tools. In my role, I continuously strive to research and translate the latest statistical and computational academic methodologies from academic literature into production. I have been with the bank for 3 years and have worked on projects spanning marketing campaign optimization, branch prospecting, and NLP / Generative AI.
I also have 3 years of professional work experience at SJI (a $2.1B natural gas local distribution company formerly known as South Jersey Industries) between my undergraduate and graduate education, where I parlayed my quantitative savvy to optimize departmental metrics across the company as a Senior Analyst and implemented a wide variety of statistical methodologies to improve performance. I was tasked with devising profitable natural gas trading strategies, developing empirical data-driven HR screening protocols, and efficiently allocating resources for the damage prevention department to minimize their risk profile through the use of machine learing, among other projects.
In addition to my time at Wells Fargo and SJI, I have consulted for various firms & individuals independently to assist with statistical modeling and automation tasks.
Graduate Education: Texas A&M University
I recently completed a Master of Science (M.S.) degree in Statistics at Texas A&M University in May 2021 where I was fortunate enough to enroll in a wide variety of coursework covering both theoretical and computational-related topics. During my first year, I served as the Lead Statistician for the Applied Cognitive & Ergonomics (ACE) lab where I oversaw analyses and ensured statistical legitimacy before publication. Throughout both Spring and Fall 2020, I have also served as a Teaching Assistant (GAT) with lab responsibilities for an Intro to Data Science Course that relies on Python programming.
I was very fortunate to have had the privilege of working alongside Dr. Irina Gaynanova as a graduate researcher to focus on applying the latest statistical methodologies to both blood pressure and continuous glucose monitoring (CGM) devices, and other technologies in the health & wearables space. With respect to CGM, I have focused on analyzing glucose level variability via sleep curves and the effect that sleep apnea has on Type II diabetics. The iglu package is available on both CRAN (ver 3.0.0) and GitHub. I am also the creator and author of the bp package, which to the best of our knowledge, is the first R package dedicated to blood pressure analysis and visualization. The bp package is also currently available on both CRAN (ver 2.0.0) and GitHub and a corresponding Shiny App is set to be published by Fall 2021.
Note: The bp package was recently presented at the 2021 R/Medicine Conference; poster can be found here.
I also had the opportunity to work as a data scientist / statistical consultant for the Texas A&M Athletics department where I analyzed athlete performance from both a physiological and strategic perspective by utilizing high-resolution spatio-temporal and physiological data, and visualizing it via Power BI for coaches and athletes. During the COVID-19 pandemic, I was responsible for utilizing contact tracing data to minimize basketball player absences during regular and post-season games by appropriately adjusting practice regimens in order to avoid SEC / safety protocol violations.
Undergraduate Education: Penn State University
I graduated from the Pennsylvania State University in 2016 where I completed over 170 credit hours towards my undergraduate dual-degrees in Economics (B.S.) and Supply Chain & Information Systems (B.S.) with a minor in Statistics, and founded the Penn State Energy Marketing Association (PSEMA). PSEMA is the university’s first research organization dedicated to collaborating on commodity market research using a variety of statistical models and computational tools to publish monthly market outlook publications.
Technical Competencies
I maintain an advanced proficiency with R, Python, and VBA / Excel having over 5 years of experience with each, but have also recently gained fluency with SQL and C++. Additionally, I have extensive professional experience with various visualization software such as Power BI, Shiny Apps, and Dash, in addition to version control software using Git/GitHub and big data tools such as Hadoop, Spark, and H2O.
Personal Research
In 2019, I rode my bicycle 5,775 miles from New York City to Seward, Alaska to collect granular health and geospatial data for research purposes. Although a pilot study in nature, the data has allowed me to employ various statistical methods to uncover insights in cardiac performance which I hope to replicate in future research with a more representative sample. I am currently evaluating options for developing a mobile application that will allow others to collect the same data to make the study more representative and will implement various machine learning algorithms to enhance personal health and wellbeing.
All of the data is publicly hosted through the Harvard Dataverse here
Check out my Power BI dashboard here or visit the dashboard tab at the top of this page.
Furthermore, check out the Code tab at the top of the page for some other programming projects I am currently working on.