NSDC 2022 Data Science Symposium | Northeast Big Data Innovation Hub

Home » National Student Data Corps » NSDC 2022 Data Science Symposium

The Data Science Symposium (DSS) is brought to you by the National Student Data Corps (NSDC), hosted by the Northeast Big Data Innovation Hub.

The DSS will provide a virtual forum for undergraduate and graduate students at public and private universities, colleges and community colleges who are interested in data science to present their research, learn about academic research best practices, network with other data science students and grow their data science knowledge and community.

The student participants, known as NSDC Explorers, will be able to choose a research topic that fits into a category that aligns with the Northeast Big Data Innovation Hub’s Focus Areas, or other areas of interest.

Congratulations to the NSDC 2022 Data Science Symposium Winners!

FIRST PLACE WINNERS

First Place is awarded to Kiet Nguyen and Zhuldyz Ualikhankyzy, a team of undergraduate students at Case Western Reserve University, for their project “Prediction of Russian ruble (RUB) against US dollar (USD) in June 2022 amid Russian-Ukrainian war.“

SECOND PLACE WINNERS

Second Place is awarded to Michele Sezgin, Vivian Almaraz, Audrey Kim, and Salwa Ouachtouki, a team of undergraduates at Smith College, for their project “Visualizing Hampshire County Schools Health Data.“

Key Dates

Students and Mentors & Judges Call for Participation Opens: February 11th, 2022 (Closed)

Student Submissions due: June 15th, 2022, 11:59 pm ET (Closed)

Student Winners announced: September 2022

Student Winners will have the opportunity to present their research at a live webinar in January 2023.

Watch this overview video for a walk-through of the NSDC Data Science Symposium:

How to Participate

If you are a student who is looking to create and present a research project as an NSDC Explorer, we welcome you to participate in the Inaugural NSDC Data Science Symposium! If you are a professional, researcher, faculty member or graduate student, we’d like to invite you to volunteer and participate as a mentor, judge, or both!

How to Participate as an NSDC Explorer

Are you an undergraduate- or graduate-level student at a public or private university, college or community college with an interest in data science? Do you have a data science research project, but do not have an outlet to present your findings? The National Student Data Corps Data Science Symposium (DSS) is here to help!

Whether you have a completed project, or you’re looking to get started on a new research idea, the NSDC will offer an extensive network of support, including mentoring calls and workshops, to help you better understand the best data science tools and techniques.

Step 1: Click on the Call for Participation Button (Students-Become an Explorer!) above to complete a short interest form!

Step 2: Review the Focus Areas and the Theme Challenges posted below. Start to brainstorm a data science research topic that interests you!

Step 3: You will be invited to join virtual mentoring sessions and workshops, hosted by NSDC HQ & Mentor Teams, to learn the best research practices and tools to help guide your project.

Step 4: Once your research is completed, you will create a virtual, one-page poster, with a recorded explanation of your research in a 3 to 5 minute audio/video presentation, and an abstract of 7 to 10 sentences to summarize your findings.

Step 5: The NSDC HQ Team will reach out to you once the Submission Form button is live! You will then submit your poster, audio/video presentation, and abstract for judging. Submissions of these materials will be due on June 15th, 2022 by 11:59 pm ET. The NSDC will then announce the winners by September 2022.

The submissions will be judged in two cohorts: the Undergraduate/Community College Cohort and the Graduate School Cohort. The top 3 winners in our Undergraduate/Community College Cohort, and the top 3 winners in our Graduate School Cohort, will receive an invitation to present their research projects live on a virtual webinar!

All participants will receive certificates of participation and may have their work published on the NSDC website.

How to Participate as an NSDC Mentor

Prerequisites: You must be an Industry/Non-profit Professional, Academic Professional, Researcher, Faculty member, or Graduate Student to participate as a mentor.

Step 1: Click on the Call for Participation Button (Mentors & Judges-Volunteer!) above to complete a short interest form! The NSDC HQ will confirm with you the role(s) you’ve chosen.

Step 2: The NSDC HQ will invite you to co-host virtual mentoring calls and workshops for interested students from February through June 2022, based on your availability. In these calls, you can share your knowledge and expertise in order to assist students with developing their research projects. This may include data science best practices, software tool tricks, or even presenting tips!

Please note: You may sign up as both a mentor and a judge!

How to Participate as an NSDC Judge

Themes & Theme Challenges

The NSDC DSS Theme Leaders have created multiple Theme Challenges, or research ideas, that you can use to create your own research project! The Theme Challenges will align with one or more of the following focus areas of the Northeast Big Data Innovation Hub, or will fall into a “miscellaneous” category if you choose another topical area for your submission. Data science can apply to many topical areas, and we want you to apply it where it aligns with your interest. We encourage you to research any approachable, appropriate topic that interests you.

The Northeast Hub founded the NSDC in 2021, and we are delighted to launch this Data Science Symposium in 2022. The Hub is a community convener, collaboration hub, and catalyst for data science innovation. The Hub amplifies successes of the community and shares credit across the community to encourage collaboration and mutual success in data science endeavors.

Learn more about the Northeast Big Data Innovation Hub’s Focus Areas.

Data Education - Student with cap and gown

Join a Theme Challenge and use the following prompts, data sets, or tools to inspire your research:

Challenge 6 (Urban to Rural Communities) – General Bikeshare Feed Specification Research

Challenge 7 (Responsible Data Science/Urban to Rural Communities) – Motor Vehicle Crash Research

Using the R programming language, use the package {njtr1} to download geotagged motor vehicle crash data. These data are compiled by the New Jersey Department of Transportation each year and are gathered from local police departments to document the location of every motor vehicle crash within the state of New Jersey. Historical data is available since the year 2001 via the package and directly from NJDOT’s crash tables website if you’d prefer not to use R. See https://doi.org/10.1016/j.simpa.2021.100176 for details on the R package for working with these data.

Develop a set of spatial risk factors using readily available public data sources (POIs, bus stops, census socio-demographic data etc.) to train a machine learning model to predict which regions and/or roads in New Jersey might be more susceptible to motor vehicle crashes. Perform feature engineering and data aggregation on the motor vehicle crash data to develop a set of predictors for your model. It is also acceptable to integrate other freely available third-party datasets as predictors so long as you have appropriate permission to use the data.

The response variable in your model should be the total count, or the relative likelihood of crashes occurring within a grid cell in the state, following the sample model code and fishnet aggregation technique implemented by Steif (2021) in R: https://urbanspatial.github.io/PublicPolicyAnalytics/geospatial-risk-modeling-predictive policing.html

Compare your model’s output to the kernel density of car accidents within the grid cells of the state to evaluate the accuracy of your model and new areas that are of high risk for future accidents. Justify your design choices and data transformations and include appropriate diagnostic visualizations and tables showing your model’s performance within the report.

Data: You are highly encouraged to incorporate many of the open datasets that are published by the State of New Jersey for this challenge. For example, the state government maintains data.nj.gov which publishes data for many state agencies. This website contains many road-related datasets that may be of interest in predicting the motor vehicle accidents. There is also the NJDEP open data portal that provides data on environmental hazards.

Challenge 8 (Responsible Data Science) – Cybersecurity Best Practices Research

Eligibility & Resources

All undergraduate and graduate students from public and private universities, colleges and community colleges are eligible to participate as NSDC Explorers in the NSDC Data Science Symposium.

All graduate students, researchers, faculty members, and industry/non-profit professionals are eligible to participate as NSDC Mentors and/or Judges in the NSDC Data Science Symposium.

Here are some resources that may help you develop a project, mentor students, or judge a submission:

NSDC Learner Central
NSDC Video Library
NSDC Slack Community: Find an NSDC DSS Channel here for all your immediate questions!
NSDC Career Panels: Recordings and upcoming events
Theme Leader Challenges: Datasets, groups and guides, and publications
Virtual mentoring meetings and workshops with industry professionals and researchers
Example Poster board
COVID Information Commons PI Lightning Talks: COVID-19 and Data Science
You are also free to use any external academic, government, and industry resources. Please cite all sources used.

Evaluation Criteria

Submissions will be evaluated by a committee of researchers and other experts on the basis of their intellectual merit and broader impact, two criteria used by the NSF to evaluate project proposals. Project submissions should clearly communicate and demonstrate a thorough understanding of the objectives, methods, and implications of data science research and make insights and recommendations that contribute to greater societal goals.

The top three projects chosen by the evaluation committee in the Undergraduate/Community College Cohort and the Graduate School Cohort will be invited to present their research and findings on a live Zoom webinar.

All participants will receive certificates of participation and may have their work published on the NSDC website.

FAQs

How should the poster board and audio/video file be formatted?

View the poster board submission template here. All graphics should be explained and cited. Your audio/video file should be 3 to 5 minutes long and should provide a presentation of your research and your findings. Please also include any necessary acknowledgements and citations on your poster board and in your audio/video file.

Stay Connected with Us

Email us at nsdc@nebigdatahub.org with any inquiries or questions.

Some ways to stay connected with the NSDC community:

Join our Slack channel
Follow us on Twitter, Instagram, or LinkedIn
Subscribe to the Northeast Hub YouTube channel
Sign up for our NSDC mailing list
Check out the REAL Volunteer Program for more collaboration opportunities
Register to Start/Join an NSDC Chapter
Register for the next NSDC Career Panel and Q&A webinar

Congratulations to the NSDC 2022 Data Science Symposium Winners!

Key Dates

How to Participate

Themes & Theme Challenges

Education + Data Literacy

Health

Urban to Rural Communities

Responsible Data Science

Join a Theme Challenge and use the following prompts, data sets, or tools to inspire your research:

Eligibility & Resources

Evaluation Criteria

FAQs

Stay Connected with Us