DC21


Awards

Grand Prize

Team DC21021: Allison Cahanin and Katherine Toren
Mentor: Quentin Read, UMD SESYNC
Dataset: Packaged Meals, Provided by U.S. Department of Agriculture
Presentation: https://github.com/allisoncahanin/packaged-meals-DC-21/blob/main/dc21-team21-preso.pdf

Best Expression of How to Cultivate Better Living

Team DC21030: Rohan Cowlagi, Ruthwik Kuppachi, Iskander Lou, and Jacquelyn Smith
Mentor: Arefeh Nasri, UMD National Center for Smart Growth
Dataset: Behavior Changes During COVID-19, Provided by UMD, National Center for Smart Growth
Presentation: https://github.com/rohanc18/UMD-Data-Challenge-21-Team-30/blob/master/Team%2030%20Data%20Challenge%20Presentation.pdf

Most Innovative Project

Team DC21029: Savia Gordon, William Grunow, Irfaan Jamarussadiq, and Tanishq Kaushik
Mentor: Derek Paley, UMD, Aerospace Engineering and Institute for Systems Research
Dataset: VeoRide E-scooter Transportation, Provided by UMD, Department of Transportation
Presentation: https://github.com/EntropicEffect/UMD_DC_2021_Team29_Presentation

Highest Quality Project

Team DC21006: Adam Levav, Junrong Liu, Ting-Yu Liu, and Walesia Robinson II
Mentor: Mestiyage Gunatilleka, UMD, Department of Mathematics
Dataset: Behavior Changes During COVID-19, Provided by UMD, National Center for Smart Growth
Presentation: https://github.com/Aurathic/UMD-Data-Challenge-2021/blob/main/DC2021_Team_6_Presentation.pdf

Best Expression of Results

Team DC21042: Manar Al-badarneh, Theodore Gaidis, Brendan Goodhue, and Gabriel Sestieri
Mentor: Akshay Mandke
Dataset: COVID-19 Global Symptoms Tracker, Provided by UMD Social Data Science Center
Presentation: https://github.com/tgaidis/UMDdataChallenge21/blob/main/Presentation%26Deliverables/Final%20Presentation.pdf

Best Team Presentation(s) – Two teams won!

Team DC21003: Fekedeselassie Kinfu, Kaveh Vakili, and Jaganathan Velraj
Mentor: Jack Molesworth, Springboard
Dataset: COVID-19 Global Symptoms Tracker, Provided by UMD Social Data Science Center
Presentation: https://github.com/jv232/DC2021_CovidTracker/blob/main/Data%20Challenge%202021%20Team%203%20presentation.pdf

Team DC21015: Zach Dorris, Ethan Levy, Claire Mytelka, and Bryan Rezende
Mentor: Miles Calabresi, Johns Hopkins University, Applied Physics Lab
Dataset: VeoRide E-scooter Transportation, Provided by UMD, Department of Transportation
Presentation: https://github.com/cmytelka/Team15-DC21/blob/main/DC%202021%20Final%20Presentation.pdf

Outstanding Undergraduate Project

Team DC21001: Grant Buttrey, Rachel Macairan, Eder Ramirez, and Sakib Sarwar
Mentor: Maria Bardossy, UMD, Robert H. Smith School of Business
Dataset: Behavior Changes During COVID-19, Provided by UMD, National Center for Smart Growth
Presentation: https://github.com/sakib-sarwar/Team1DataChallenge/blob/master/NEW%20Behavior%20Changes%20During%20COVID-19.pdf

Outstanding Graduate Project

Team DC21061: James Maslek
Mentor: Alex Din, U.S. Department Housing and Urban Development
Dataset: Opportunity Zones, Provided by U.S. Department Housing and Urban Development
Presentation: https://github.com/jmaslek/UMD_DataChallenge/blob/master/FinalPresentation_no_plotly.pdf

Outstanding Combined Undergraduate and Graduate Project

Team DC21035: James Boggs, Ziqin Ni, and Madeline Raith
Mentor: Angela Ambrosi, UMD, Graduate School
Dataset: VeoRide E-scooter Transportation, Provided by UMD, Department of Transportation
Presentation: https://github.com/jboggs1/DataChallenge2021/blob/main/TeamMaddy_DataCompetition2021.pdf


Datasets

1. Organization: Organization: Montgomery County Commuter Services (MCCS)

  • Project Name: Transportation Management
  • Description: In Montgomery County, Transportation Demand Management (TDM) programs have been focused on major activity centers where high density commercial and residential land uses are located – and where traffic congestion has been most significant. TDM programs are used as an effort to reduce traffic congestion, improve air quality, and promote sustainable land use and transportation patterns. The County hopes to understand how its efforts to reduce transportation impacts, using TDM programs to achieve a certain percentage of Non-Auto Driver Mode Share (NADMS), translates into savings in Vehicle Miles of Travel (VMT). The dataset contains 350 variables representing survey questions and 11,400 rows. There are seven years of survey data to choose for comparison.

Team Projects 


2. Organization: UMD National Center for Smart Growth (NCSG)

  • Project Name: Behavioral Changes during COVID-19
  • Description: Researchers from UMD’s National Center for Smart Growth (NCSG) designed a survey to investigate the influence of the pandemic and statewide stay-at-home orders on the way people travel to meet their essential needs, do their routine daily exercises, and get to work—if employed in an essential service sector. Monitoring and analysis of the changes in travel behavior and the level of physical activity would be beneficial in many ways; it would help for a more efficient and comprehensive analysis of the various impacts the current situation has on transportation needs, and physical and mental health, and would help us better plan and manage future situations. The dataset can be used for analysis of influence of physical activity on physical and mental health, socio-demographic characteristics on general behavior changes, and other topics of interest. Between April 10th, 2020 and July 8th, 2020, 587 responses were collected from all around the country while the final dataset contains 564 rows with 29 variables representing the 26 survey questions.

Team Projects 


3. Organization: United States Department of Agriculture (USDA)

  • Project Name: Packaged Meals
  • Description: Over the past several decades, Americans have grown to rely on the convenience of foods prepared outside of the home. Since 2018, USDA released a branded food product database (BFPD) which is the result of a Public-Private Partnership, whose goal is to enhance public health and the sharing of open data by complementing USDA Food Composition Databases with nutrient composition of branded foods and private label data provided by the food industry. A subset of data was prepared from BFPD to include categories that relate to packaged meals. The Department of Agriculture would like help in identifying the most popular ingredients and the combinations of those ingredients. Agencies can use this information for nutrition stability of these products while manufacturers can develop plans for future production. There are 13 variables and 4,438 rows in the dataset.

Team Projects 


4. Organization: Social Data Science Center (SoDA)

  • Project Name: COVID-19 Global Symptoms Tracker
  • Description: University of Maryland’s Joint Program in Survey Methodology and Carnegie Mellon University’s Delphi Research Group, collaborated with Facebook to invite people to participate in surveys that ask about how they are feeling, including any symptoms they or members of their household have experienced and their risk factors for contracting COVID-19. The surveys are designed to provide valuable information to help monitor and forecast how COVID-19 may be spreading. The organization is interested in learning what insights policymakers can use to determine where to send resources and what patterns are present in changing attitudes toward COVID and physical distancing.  All datasets include 20 variables while rows vary from 27 to 65,000 rows depending on month and area. Surveys range from April to November of 2020 and are separated by country and region.

Team Projects 


5. Organization: UMD Department of Transportation Services (DOTS)

  • Project Name: VeoRide E-scooter Transportation
  • Description: The company that provides the e-scooter service in the UMD area, VeoRide Inc., is a mobility service provider that manages their micro mobility fleet through the use of the Mobility Data Standard (MDS). Data generated from individual e-scooters and stored in VeoRide’s computers contain the information necessary for this study. The dataset comprises 62 days (October 2020 and October 2019) of historical data, to include ride counts, event times, trips, routes, and status changes. The Department of Transportation Services would like to know how the publicly available e-scooter service available on campus provided by VeoRide Inc., supplements the campus transportation network. Within the timeframe of the data, there are 14 variables and 40,325 rows of recorded rides.

Team Projects 


6. Organization: The U.S. National Cancer Institute (NCI)

  • Project Name: Health Information National Trends Survey (HINTS 5, Cycle 3)
  • Description: The U.S. National Cancer Institute (NCI) has been conducting the Health Information National Trends Survey (HINTS) since 2003 to learn about U.S. adults’ cancer-related perceptions and knowledge, their health behaviors, and their health-related information access, needs, seeking, and use. This dataset was released in  January 2021 and contains data that was collected between February and June 2020. NCI is looking for analysis of respondents’ internet use, use of social networks, knowledge of clinical trials, political viewpoints, and other factors compared to feelings of frustration, anxiety/depression, or their confidence in their ability to take good care of their health. The dataset includes data from a total of 3,792 completed questionnaires and 73 partially completed  questionnaires, for a total of 3,865 questionnaires (rows) and 438 variables of interest.

Team Projects 


7. Organization: United States Department of Housing and Urban Development (HUD)

  • Project Name: Opportunity Zones
  • Description: Opportunity Zones are a place-based incentive that were created by the Tax Cuts and Jobs Act of 2017. This incentive allows investors to allocate unrealized capital gains into Qualified Opportunity Funds to invest in Qualified Opportunity Funds. Governors of each state were able to propose up to 25% of low-income census tracts to be Opportunity Zones. States were also eligible to nominate contiguous census tracts adjacent to low-income census tracts if the adjacent census tract had a median family income within 125% of the eligible low-income census tract and the eligible low-income census tract was selected. Students are expected to be able to link/join/merge other datasets to the Opportunity Zone Eligible Census Tracts dataset and identify any trends using Census and/or American Community Survey data. The Opportunity Zone dataset contains 17 variables and 72,882 rows. There are 3 American Community Surveys, each with 73,764 rows and between 127-248 variables.

Team Projects 


Dataset Levels


Level 1: Participants with little to no knowledge in data science. The problem statement is straightforward about what the final product may look like. The dataset contains enough information to answer the questions in the problem statement. Start from the basics and create an interesting story.


Level 2: Participants with basic data analysis knowledge. The problem statement is open-ended yet straightforward. The dataset has a standard structure suitable for beginners. Creative and interdisciplinary solutions are welcomed.


Level 3: Participants with some data analysis background. The problem statement is open-ended about what the final product may look like. The dataset may contain many variables of interest. Analyses from different angles by various techniques are encouraged.


Level 4: Participants with advanced data analysis skills. The problem statement is open-ended and requires multitudes of analytical perspectives and visualizations. Statistical modeling is highly recommended.


Level 5: Participants with advanced data analysis knowledge and skills. The problem statement includes requirements of modeling. The dataset has a complex structure, numerous variables of interest, and spatial-temporal dimensions.