You are here: Â鶹´«Ã½ Academic Programs Shared Data Science Data Science Projects

Selected Practicum & Thesis Projects

Xamine Your WorldHelps students, teachers, and stakeholdersÌýimprove data literacy skills

  • °ä°ù±ð²¹³Ù´Ç°ù²õ:ÌýMS students Haiman Wong, Jingyi Xu, Doudou Shi, Elizabeth Marge
  • Overview: XamineYourWorld uses 2020 Decennial Census Data and ACS Data to help K-12 students, teachers, and education stakeholders build data literacy skills through analyzing, assessing, and taking action with data visualizations. Developed for the Census Bureau Opportunity Project, fall 2021. See theÌýÌý²¹±è±è.
  • See also:Ìý

SunnyRHelps helps educators and students in Puerto Rico promote resilience by analyzing potential behavioral disorders and apt resources

  • Creators:ÌýMS studentsÌýMeera Patel, Lindsay Beyak, Jonathan Hague
  • Overview: SunnyR is a Digital tool designed to helps educators and students ages 12-17 face adversity and promote resilience by analyzing potential behavioral disorders and finding resources. Mindful activities may also be encouraged in the classroom to promote a healthier learning environment and a safe space. If appropriate, educators may also provide information discovered with this app to parents/guardians of targeted youth. Developed for the Census Bureau Opportunity Project, fall 2022.

AirMotionDCMonitoring and analyzeÌýtraffic patterns, air pollution and weather

  • Creators: MS studentsÌýChace Paulson, Minh-Tuan Nguyen and BS Stats/Health student Shalini Ramachandra
  • Overview: AirMotionDC compiles and visually displays real time data on traffic patterns, air pollution, and weather in the District of Columbia to explore the relationship between transportation and air quality locally, at both a granular level and citywide levels. Developed for the Census Bureau Opportunity Project, fall 2021.
  • Charles Ingulli: An R Package for Managing Longitudinal Survival Data: LSDWrangling, supported by a Department of Mathematics and Statistics Summer Research Award, summer 2020.

    °¿±¹±ð°ù±¹¾±±ð·É:ÌýSurvival analysis data may come in different usable forms. Transitioning between formats requires detailed knowledge of how information is parsed and how variables are treated. The wlsd package in R provides methods for transforming data between usable formats to ease this process. wlsd can transition between the counting process format and longitudinal or panel format as well as setup data suitable for count data regression.Ìý
  • Allison Ragan: Child Abuse and Neglect in the United States: A Visual Exploration. Supported by Mellon Grant,Ìýspring/summer 2021.
  • Egzona Rexhepi:ÌýIndependent Vector Analysis with Sparse Inverse Covariance Estimation. MS thesis, fall 2022ÌýAdvisor: Zois Boukouvalas.Ìý
  • Zachary Nadrich: A Spatial-Temporal Markov Random Field Model. ÌýMS thesis, fall 2020. Advisor: Michael Baron.
Data Science Census Bureau Opportunity Project

Xamine Your World app, developed by MS students for the Census Bureau Opportunity Project.

Projects Gallery

Exchange Rate Indicators Genaro Villa
Ìý

The Exchange Rate Indicator appThe Exchange Rate Indicator app shows the price change in the British Pound vs. the US Dollar over December 2019.

Epicurious Recipe Analysis Waseem Aburakia-Einhorn, Ethan Willing, and Stephen Kelly
Ìý

Epicurious Recipe Analysis App. The Epicurious Recipe Analysis App displays data such as rating, protein, and calories.

Gun Deaths Alexa DiBenedetto and Danya Murali
Ìý

Gun Crime Data Visualization Alexa di Benedetto and Danya Murali's project analyzed over 100,000 gun deaths in the US between 2012 and 2014.

Stock Trends Following Backtester Yanfeng Chen and Lange Kaupinen
Ìý

Backtesting using Moving Average Crossovers

Yanfeng Chen and Lange Kaupinen examined strategies for trading stocks based on where stock prices are compared to their moving 10 year average price. The strategies were compared by doing a "what-if" the stocks had been bought and sold on that basis and compared to historical prices.

Data Science Careers Hafid Pradipta
Ìý

sdfaHafid Pradipta reviewed data science practitioners demographics, learning platforms, programming languages, job skills, biggest challenges and other factors from a 2017 study of 16,000 respondents in 171 countries.

Medical Device Reports Nathan Smith
Ìý

MDR Text MiningNathan Smith mined keywords from professional literature on medical devices.

Soccer Strategy Julia Smadja, Devika Nair, and Dominic Thomas
Ìý

Soccer strategy analytics tool. The soccer project looked at DC United soccer data to analyze game strategy of soccer matches.

Global Terrorism Sean Curl and Steven Aguilar
Ìý

Global Terror Attack Time Series Sean Curl and Steven Aguilar analyzed data from the Global Terrorism database with over 100 variables for location, targets, outcomes, and more.