Capstone Project

The Capstone Project marks the culmination of the Master of Data Science program, offering students a hands-on opportunity to solve real-world data science challenges with industry partners. These projects allow students to demonstrate their expertise across data science, from data gathering to analysis and interpretation. Working in small teams, students apply comprehensive analytic processes, including data collection, transformation, visualization, and model development, to deliver actionable solutions to sponsoring organizations.

A successful capstone project requires students to define the problem, conduct exploratory data analysis, clean and visualize data, and select appropriate methods for analysis. Techniques may include machine learning models or statistical analyses, with each step documented to ensure clarity and reproducibility.

The final presentation or report includes visualizations that illustrate the results, a discussion on findings’ implications, limitations, and future research directions. Students also provide the analysis code and documentation to support transparency. Effective communication of technical insights to non-technical audiences is emphasized, preparing students for industry demands.

Sample Projects from 2022:

• Using natural language processing (NLP) from clinical notes to predict newborn intensive care unit (NICU) readmits.
• Detecting a pandemic early through social media classification.
• Using factor investigation to analyze the sleep of pregnant women.
• Detecting patent ductus arteriosus (PDA) in echocardiograms using deep learning.
• Assess real-time mental health resources using Machine Learning.
• Exploring the effects of social determinants of health on health outcomes in patients with obesity or major depressive disorder.

Sample Projects from 2023:

• Deploying Open Source LLM into Municipality.
• Prison Mental Health Assessment during Pandemic.
• Utilizing Sound Waves for Geolocation Analysis.
• Statistical Analysis on Language Development in Infants.
• Social Determinants on Health and Long Covid.
• Utilizing AI to Categorize and Diagnose Autoimmune Diseases from Raw Images.
• Multi-Model Analysis on Re-incarceration in the U.S.