DSC @ NYU 2020 Datathon
DSC @ NYU 2020 Datathon
November 20-21, 2020
Hosted by the Data Science Club at NYU
In association with Understood.org
This webpage will continuously be updated so please check back soon for more details.
Datathon Primary Directive
Tasks:
- Build an automated tool to create and populate a dataset of companies that have potential to partner with Understood.org.
- Build logic for Understood.org to score how closely each company aligns with their mission statement.
- Your approach should be built with latency in mind although the way you score how each company aligns with Understood is up to you.
- Feel free to explore the content of the websites of the companies you look at. NLP projects may flourish here.
- Feel free to add as many features as possible.
Feel free to use any data and coding language at your disposal. Some sample websites where data can be found are listed below:
- https://projects.propublica.org/nonprofits/
- https://www.globallearninglandscape.org/
- https://www.sec.gov/edgar.shtml
Examples of companies who align with Understood’s mission statement: National Center for Learning Disabilities
Examples of companies who do not align with Understood’s mission statement:Exxon Mobile
Scoring
- How many useful entities (rows) and features (columns) can you bring to the dataset?
- Is the information usable in the long term? Can it be refreshed as it gets outdated?
- Latency of your model
- Can you identify for-profit and non-profit entities that are aligned with Understood.org's mission?
- Can you identify how close each company is to Understood's mission
Submission
Submissions will ideally be in a csv format.
Team Information
Datathon Schedule
| Time (EST) | Event |
|---|---|
| 14:00 | Introduction with Understood.org |
| 15:00 | Discussion and Q&A with Understood.org |
| 16:00 | |
| 17:00 | Team Spirit Award Introduction with Kenan Anderson |
| 18:00 | Team Spirit Challenge |
| 19:00 | |
| 20:00 | Q&A hosted by NYU Bobst Data Science Specialist Vicky Steeves Team Spirit Challenge |
| 21:00 | |
| 22:00 | Team Spirit Challenge |
| 23:00 | |
| 00:00 | Team Spirit Challenge |
| 01:00 | |
| 02:00 | Team Spirit Challenge |
| 03:00 | |
| 04:00 | Team Spirit Challenge |
| 05:00 | |
| 06:00 | Team Spirit Challenge |
| 07:00 | |
| 08:00 | Team Spirit Challenge |
| 09:00 | |
| 10:00 | Team Spirit Challenge |
| 11:00 | Q&A hosted by NYU Bobst Data Science Specialist Vicky Steeves |
| 12:00 | Team Spirit Challenge |
| 13:00 | |
| 14:00 | Team Spirit Challenge |
| 15:00 | |
| 16:00 | Team Spirit Challenge |
| 17:00 |
Workshop
Datathon Day 1
Kick-off!
Introduction to the Understood Team
Evaluation Criteria - by the Understood Team
The Current Database - by the Understood Team
The Task - by the Understood Team
Company Examples
Q&A and General Guidance (Highly Recommended)
Closing Remarks
Support Staff Schedule
| Time (EST) | General/FAQ Support | Understood.org Support | Github Support | Ask a Grad Student | Ask a Librarian |
|---|---|---|---|---|---|
| 14:00 | Aditya, Kenan, Ethan | Understood.org Staff | Reema | ||
| 15:00 | Aditya, Kenan, Ethan | Understood.org Staff | Reema | ||
| 16:00 | Aditya, Kenan, Ethan | Reema | |||
| 17:00 | Aditya, Kenan, Ethan | Reema | |||
| 18:00 | Aditya, Kenan, Ethan | Reema | Dhara Mungra | ||
| 19:00 | Aditya, Kenan, Ethan | Reema | Christina Dominguez | ||
| 20:00 | Aditya, Kenan, Ethan | Vicky Steeves | |||
| 21:00 | Aditya, Kenan, Ethan, Mindy | Hyun Jung | |||
| 22:00 | Aditya, Kenan, Ethan, Mindy | Sudharsan Asaithambi | |||
| 23:00 | Aditya, Kenan, Ethan, Olivia, Mindy | Sudharsan Asaithambi | |||
| 00:00 | Kenan, Olivia, Mindy | ||||
| 01:00 | Kenan, Olivia, Mindy | ||||
| 02:00 | Olivia | ||||
| 03:00 | Olivia | ||||
| 04:00 | Olivia | ||||
| 05:00 | Olivia | ||||
| 06:00 | Mindy | ||||
| 07:00 | Mindy | ||||
| 08:00 | Mindy | ||||
| 09:00 | Olivia, Mindy | ||||
| 10:00 | Olivia, Mindy, Areeb | Anu-Ujin Gerelt-Od | |||
| 11:00 | Aditya, Kenan, Olivia, Mindy | Vicky Steeves | |||
| 12:00 | Aditya, Kenan, Olivia, Mindy | ||||
| 13:00 | Aditya, Kenan, Ethan, Mindy | Reema | Dhara Mungra | ||
| 14:00 | Aditya, Kenan, Ethan | Reema | |||
| 15:00 | Aditya, Kenan, Ethan | Reema | Christina Dominguez | ||
| 16:00 | Aditya, Kenan, Ethan | Reema | |||
| 17:00 | Aditya, Kenan, Ethan | Reema |
Contact Information
Important Slack Channels to Join
Ask a Grad Student Slack Channel
FAQ’s
When is the event?
The event will be Friday 11/20 from 2pm EST to 11/21 5pm EST.
----------------------------------------------------------------------------
How long is the event?
The event will be 27 hours starting at 2pm EST on Friday 11/20 and submissions will close at 5pm EST on 11/21. Working for the entire length of the event is not required. Coordinate with your team to find times that work for everyone.
----------------------------------------------------------------------------
Where is the event being held?
The event will be virtual with all necessary information on this Github page. The workshop for this will be on Youtube here. and can also be found embedded on this page. All other activities will be held on the Zoom for the event at here. This is where we will first assemble at 2pm EST on Friday where Understood.org staff will kick off the event. All meetings with event organizers and support staff will be through this Zoom call which will be on for the whole 27 hours. Breakout rooms for each team will also be available for the duration of the event, so you and your members can use the breakout rooms to collaborate and pop in and out of the general lobby to ask questions or to join the fun social events. Basically – you and your team can work in the breakout rooms of the same call, and then chill or ask questions in the general meeting room of the same link.
----------------------------------------------------------------------------
Who is hosting the event?
This event is a 3-way collaboration between Data Science Club @ NYU, Understood.org, and NYU Bobst Library. Understood.org will be running the datathon, providing assistance throughout the event, and evaluating the work of participants. NYU Bobst will be hosting the technical workshop as well as a Q&A. DSC is putting all this together, providing graduate student level tech assistance and managing all teams and other stakeholders.
----------------------------------------------------------------------------
Where is the workshop being held?
The workshop will be uploaded Friday 11/20 night on Youtube here. . A text version of the "collaborating on github" workshop has also been provided here. If you have any questions about the content of the workshop feel free to message the "ask-a-librarian" channel on Slack. Tech/workshop-related questions will be answered by our Data Science Specialist Librarian Vicky Steeves between 8-9pm ET on Friday and 11am-12pm on Saturday. Other times, the DSC E-board and CDS graduate students may help you out.
----------------------------------------------------------------------------
What assistance will be provided during the event?
Understood.org staff will kick off the event with an introduction on Friday 11/20 at 2pm EST and will be around for Q&A and discussion until 4pm EST. We are joined by Francisco Arceo from the data science team, Preeya Goradia from the impact/ecosystem team, and Haftan Eckholdt who leads both of these teams. They may also be reached over the weekend through the "Ask-Understood" Slack channel. Graduate students will also be available over Zoom during designated timeslots throughout the event. A "Ask a Graduate" slack channel will also be available. A Q&A will also be hosted by NYU Bobst Data Science Specialist Vicky Steeves during the event. E-Board members will be available over Zoom for the full event time. Check the posted schedule for exact times.
----------------------------------------------------------------------------
What are the prizes?
Winning teams will receive Center for Data Science merch as well as prizes from Understood.org.
----------------------------------------------------------------------------
How is the datathon being judged?
Understood.org evaluates the projects of the participants. More information will be provided on the day of the datathon. There will also be a community award for participating throughout the datathon. Refer to the schedule and slack for events hosted with our Director of Events, Kenan Anderson.
----------------------------------------------------------------------------
What is the team spirit award?
The team spirit award is given to the team who participates the most in the social events held over the course of the datathon. More information will be given at 17:00 EST over Zoom. Make sure to participate as there will be prizes!
----------------------------------------------------------------------------
When will winners be announced?
Top teams will be emailed and winners will be formally announced by the following week.
----------------------------------------------------------------------------
Who can participate?
This event is open to all current NYU students. Being a declared data science major or minor is not required.
----------------------------------------------------------------------------
How big can my team be?
Suggested team size is 3-6 members. You can work solo if you wish.
----------------------------------------------------------------------------
How do I form a team?
If you are looking for teammates, reach out through the Hackathon-Team-Formation channel on slack or grab your friends! If you have not signed up for the Data Science @ NYU slack yet, the link is here.
----------------------------------------------------------------------------
What if I don’t have a team by the start of the event?
If you want a team, but do not have one yet please sign up using the link here. From here, people can message you about joining their team. Otherwise, we will reach out to all registrants not a part of a team by Thursday to team up if they did not want to work solo.
----------------------------------------------------------------------------
Where can I sign up?
Sign-ups for this event have closed. </a> If you have a team already formed please make sure to sign up here. If you do not have a team yet but are interested in joining a team, please use the second sheet on the spreadsheet to put your contact information in.
----------------------------------------------------------------------------
Where can I collaborate with my team?
Since this is a remote hackathon, feel free to use whatever platform you like. Zoom breakout rooms for each team will be provided. Feel free to hop on and off Zoom at your leisure. Additional recommended platforms include: Discord, Slack, Groupme, Messenger, and Github.
----------------------------------------------------------------------------
Flyers
