Mary Solomon

EASY Model

The Encounter Appropriateness Score for You (EASY) Model is a clinical decision-support tool that predicts telehealth appropriateness for future visits based on factors such as diagnoses, medications, patient encounter data, and provider preference.

The development and pilot implementation of this model is published in the Arthritis Care and Research journal. Lastly, the EASY Model is the recipient of the Duke Institute for Health Innovation (DIHI) RFA 2023 grant.

Multivariate Analysis of K-Pop Audio Features

This project was completed for the master's thesis of my applied statistics degree at BGSU. I curated dataset of 12,012 Korean pop songs and their audio features using Python and Spotify API. Then, I applied advanced statistical methods such as regression, clustering, PCA, and hypothesis testing to extract insights on how audio features define the genre of K-pop and contribute to its global popularity.

Receipient of the 2nd place paper presentation award at the BGSU 2021 Charles E. Shanklin Graduate Symposium.

American Soldier in WWII

Completed with the Data Science for Public Good program, this project leverages natural language processing (NLP), computational text analysis and social network analysis to glean insights into American soldiers’ attitudes about racial and ethnic relations as well as gender relations during World War II. The dataset is sourced from a unique and historic collection of “attitude surveys” that were administered to hundreds of thousands of American Army troops during the war in 1943. This project is part of the larger multi-institutional American Soldier in WWII project funded by the National Endowment for the Humanities.

Economic Mobiltiy of South Wasco

Developed a dashboard, using R (Shiny), to provide community decisionmakers of South Wasco, Oregon with baseline datasets and comparative analyses of the likely factors affecting economic mobility. Curated analytical datasets from local and federal datasets (American Community Survey) with R and the US Census API. This project was completed in collaboration between Cooperative Extension, South Wasco Alliance, and the University of Virginia Social Decision and Analytics department.

Market Research of Concert Attendance at BGSU

Independently conducted marketing analytics study that delivered actionable insights on increasing concert attendance at the BGSU College of Music. Designed, administered, and collected user surveys with Qualtrics and R. Analyzed surveys using A/B testing and Exploratory Data Analysis (EDA).