Get Involved
top of page

Second-Year Surge: After the AP Data Science Challenge Captivates 9000+ Students!

In its second year, the After the AP Data Science Challenge exploded in popularity, highlighting the desire from high school students to learn data science

Varunrao Wallajabad and Saketh Subramanian discuss their predictive models in class at Fort Zumwalt West High School

The future of work is rapidly evolving, with data science emerging as a cornerstone of the digital economy. In 2023, 22% of job postings across the country sought workers with at least one skill related to getting, exploring, or analyzing data. Yet, fewer than half of U.S. universities currently offer specific initiatives to equip students with the data skills necessary to thrive in an economy where AI and machine-learning are on the rise.

This gap in education underscores the importance of initiatives like the After-The-AP Data Science Challenge, which empower high school students to develop essential data science skills early in their academic journeys. Now in its second year, the After-The-AP Data Science Challenge has grown exponentially, from 2,500 student participants in 2023 to over 9,000 student participants in 2024. This surge in participation reflects the growing interest and importance of data science education among high school students.

In collaboration with Data Science 4 Everyone at The University of Chicago, CourseKata, and North Carolina State University Data Science Academy, Skew the Script – a nonprofit education initiative led by a consortium of AP Statistics educators – first organized this national competition for high school students following their AP examinations in 2023.

In 2024, 488 classrooms from across the United States and its territories registered for a competition to predict which colleges offer the highest return on financial investment by developing models to forecast student loan default rates. Using data from the U.S. Department of Education’s College Scorecard and IPEDS portals, students performed complex data analysis, filtering, modeling, visualization, and communication of insights on U.S. colleges. They navigated 26 variables across 4,435 colleges, carefully selecting valuable information for their final submissions. Students boldly tackled this challenge in the several weeks they were allotted to devise their own unique solutions. 

(From left to right) Varunrao Wallajabad, Brady Willman, and Saketh Subramanian swap insights and collaborate.

Among the many participants across the country, Boyu Hua, who took first place in this year's challenge, emerged as a standout, mastering diverse modeling approaches that proved both rewarding and challenging. When asked why he chose to participate, Boyu cited his own interest in working on real-world problems in the classroom: “The chance to work on practical data science projects and engage with instructors on topics beyond the syllabus was incredibly appealing. I wanted to challenge myself, broaden my skills in coding and statistics, and see how far my accumulated expertise in data science could take me.”

 "I believe the best learning is experiential whether it's a semester project or the After the AP Data Science Challenge where students, like Boyu, can get their hands 'dirty' analyzing and interpreting real-world data."

With his model achieving an impressive final test R^2 value of approximately 0.92, Boyu exemplifies the innovation and skill nurtured through the challenge. Reflecting on Boyu's achievement, his teacher Ed Leonard of St. Martin’s Episcopal School remarked: "Boyu is a truly remarkable young man with an incredible future. I can't wait to see what path he chooses. I believe the best learning is experiential whether it's a semester project or the After the AP Data Science Challenge where students, like Boyu, can get their hands 'dirty' analyzing and interpreting real-world data. I'm very proud Boyu jumped right in and took on the Challenge while also tackling four AP exams."

Boyu Hua hard at work on his predictive model

Using Jupyter Notebooks and R, an open-source statistical software, students like Boyu engaged in complex data analysis techniques using digital technology, advanced algebra, and complex statistical techniques. For students to succeed in the challenge, mastery of linear regression, polynomial regression, and the basics of machine-learning  were all required.

Aaron Ho, who secured the second-place spot, shared his motivations and insights for joining the 2024 After the AP Data Science Challenge:

"Originally, this was an assignment given to me by my teacher, Mrs. Anthony, but as I progressed through the challenges, I found that this was something that I could use to apply my knowledge of Computer Science, something that I've been striving to do ever since I took AP Computer Science. I got really into it, and it became something that I worked very hard on. Maybe a little too hard!"

"Completing this challenge has opened a whole new window for me. I can see myself studying Data Science along with Computer Science or Cybersecurity in the future." - Aaron Ho

One unique element of the After the AP Data Science Challenge is the collaborative nature of the project, which invites students to work together in learning the ins-and-outs of data analysis and modeling, before eventually submitting their own individual models to the competition.

James Kwong, who secured eighth place in the competition, said he was drawn in by the appeal of collaborating with his classmates: “ The collaborative environment where all of my fellow Stats students, from all four of our periods, were grinding out each module together just made the experience really fun. We had this class leaderboard thing, and that really motivated me to get the top spot.” Though he also added that he and his classmates made memories working together outside the classroom as well, "I would say the most memorable moment would be coding this on the sofa of my friend's house! We were eating cookies together, and watching TV, the lights were all off, and it was generally just a great time."

"This experience has shown me that those seemingly dull numbers can tell fascinating stories."

For some students, the challenge revealed how data science can be used across curriculum, as sixth-place winner Hagen Qian noted: “This challenge showed me that you can apply data science to any topic and be able to notice trends with different variables.”

Ibrahim Ahmad, who secured sixth place, also said participating in the challenge transformed the way he perceived data science and drove home the idea that data science can bring math to life: "Before this challenge, I believed data science was simply sifting through endless, monotonous files filled with numbers. However, this experience has shown me that those seemingly dull numbers can tell fascinating stories. The data speaks to us, and by analyzing it, we can uncover narratives that offer profound insights into our lives and the world around us."

"I am so delighted that this challenge exists since it gives students a chance to learn some basic R programming while reinforcing their statistical conceptual knowledge." 

Jeremy Gibbs, a veteran AP Computer Science teacher at Fort Zumwalk West High School whose students Varunrao Wallajabad and Jaineel Patel placed in the top 12, encouraged other teachers to consider joining next year’s challenge: 

“I am so delighted that this challenge exists since it gives students a chance to learn some basic R programming while reinforcing their statistical conceptual knowledge. My biggest advice was echoed by [my student] Jaineel, 'Just do it!'  This really was a valuable learning experience for my students and myself.  I look forward to keeping the tradition going next year!”

For future participants, second-place winner Aaron Ho offered this inspirational advice, pushing students to go beyond their own perceived limitations: "There is so much you can do if you put your mind to it. Never be afraid to challenge the boundaries; but make sure not to break the rules. In my model, I strayed away from the traditional addition and subtraction, and moved on to complex interactions, and used multiple operands. Don't be afraid to use your intuition as to what will work. It's certainly what propelled me into this year's second-place spot."

Among students from over 46 states (and several territories outside the US) and hailing from a range of academic backgrounds (ranging from course-completers in AP statistics, AP Computer Science, and AP Calculus) we are pleased to announce our 2024 National Data Science Challenge Champions:

We’d also like to congratulate the runners-up of the challenge, who submitted highly predictive and accurate models for the same task, just barely missing the leaderboard:

  • Andrea Zhang, Western Reserve Academy

  • Kate Guglielmo, Westfield High School

  • Ethan Alapatt, Mission San Jose High School

  • Ameen Almousa, Franklin High School

  • Davin Huynh, Liberty High School

  • Jake Evans, Chagrin Falls High School

  • Mia Chavez, Summit High School

  • Nicolas Oncken, Cascades Academy

  • Kai Deshima, Somerville High School

  • Josh Jensen, Broad Run High School

  • Aadi Gupta, Mission San Jose High School

  • Abhay Bhaskar, Edison Academy Magnet School

  • James Leung, Hunter College High School

  • William Stinson, Chagrin Falls

  • Deslderio Anderson, Franklin High School

On behalf of the national organizers, we congratulate each student team who participated in the challenge – choosing to dedicate their class time at the end of the school year, when time and perseverance are the hardest to find. Thank you for diving in and engaging in valuable skills that will carry with you for the next several years, and long into your career – in addition to learning about the complicated landscape of college debt.

Thank you for your efforts, and we know this is just an early preview of what you will accomplish in the future!

1,821 views1 comment

1 Comment

Congrats to all these obviously very dedicated students.

bottom of page