Skip to main content
University of Rochester

Goergen Institute for Data Science

News & Events

Use real data to help increase U.S. high school graduation rates to 90% by the year 2020.

August 25, 2015 - November 10, 2015

Use real data to help increase U.S. high school graduation rates to 90% by the year 2020.

It’s no secret, a high school diploma matters -- to individuals, communities, and society. United States high school graduates are more likely to be employed and less likely to engage in criminal behavior. They also enjoy better health and longer life expectancy, and are more likely to be engaged in their communities. 

At AT&T, we believe that all students deserve the tools to help them reach their full potential. AT&T Aspire is our signature education initiative that drives innovation in education by bringing together diverse resources that focus on high school graduation and career readiness. This includes funding, technology, employee volunteerism, and mentoring.

To meet the GradNation Campaign goal of 90% graduation rate by 2020, we need to identify every opportunity that can create success for our nation’s youth. Income, demographics, family dynamics and zip code are all known factors that can play a significant part in a student’s ability to graduate. But what are the unknown factors? Does bullying play a part? Crime? What about local gas prices, weather or transportation factors? Help us figure it out.

We need to make some big bets on innovative new ideas and solutions to reach 90%. Now is your chance to make a difference -- not only for today’s students, but for generations to come.

The Approach

Here’s the good news, we’ve already identified two distinct approaches for tackling this challenge:

  1. The first is to use our pre-built dataset, which includes graduation data joined with the maximum overlapping Census data.
  2. The second is to take a more in depth look at our graduation problem. We’ve provided the individual data sets that we used to join the graduation data and Census data together. In addition, we’ve also provided the mapping logic that includes information about every Census tract that overlaps each school district. We highly encourage you take these all into account.
Ready to get started?

Check out the requirements below and then head to the Resources page to check out the current problem state, the required datasets, sample benchmark analyses, and more!

View full rules

ELIGIBILITY

This challenge is open to:

  • Individuals (who have reached the age of majority in their jurisdiction of residence at the time of entry); Teams of eligible individuals; Organizations (up to 50 employees)
  • Organizations with over 50 employees may compete for the non-cash Large Organization Recognition Award.
  • Eligible individuals or teams of eligible individuals who are employed by AT&T may compete in the AT&T Employee Awards prize track.

REQUIREMENTS

Main Requirements:
  1. Analyze - Using one or more of the provided public datasets (along with any other public datasets you choose), incorporate data science, data visualization, and ideation into a compelling argument that will help increase high school graduation rates.
  2. Create - Highlight your insights in a static or interactive data visualization, OR a data-centric, functional software application.
Submit the following:

Text Description. In your text description, include a write-up on your methodology (including the modeling approach of choice for predictive modeling) as well as anything you did for data cleaning and/or feature engineering.  

In regards to modeling results (20% of grade) description, please provide your predictive analysis results of the ‘required data sets,’ such as which variables turned out to be predictive, what additional data were you able to add to these data sets, and how did that improve the predictability? Please state specifically how your model results compared to the benchmark results provided. 

Please also note that models are more useful if the key predictive variables in them point to potentially actionable things that can be done with the insights provided by your model to improve the graduation rate. Hence, this is why the actionable insights description amounts to 40% of the overall score. Please describe in detail which variables in your model are potentially actionable, and what specific actions either an individual, family, community organizations, school district, administration, local or federal government, etc. could take in order to improve the graduation rate by acting upon the insight provided by the  predictive variables in your model. 

Please additionally also include explanations about each of your data visualizations in the text description area.

A Demo Video. (hosted on YouTube, Vimeo, or Youku. Your video should include an explanation of the data used, an explanation of the analysis, and a walk-through demo of the visualization or application. Videos should be 5 minutes or less.

Images/Visualizations. You must also submit at least one image/screenshot of your working data-centric application or interactive data visualizations, or all of your static data visualizations.

Code and Install files. You must upload your analysis code into your submission for judging purposes (this will not be made public). If your submission includes a data-centric software application, you must also provide us with a way to test your application.

New & Existing Apps:

Submissions may be newly created or pre-existing. If submitting an existing app (developed prior to this competition), the submitter must have integrated one or more of the required datasets and new functionality or analysis after the start of the submission period.

Category: Other

Events