SUCHETA SRIKANTH, a junior at NRHS, won first place in the National High School Data Science competition for creating an accurate AI/ML model that analyzed a dataset to predict the “college happiness score.” Offering their congratulations to Srikanth (center) were (at left): physics teacher Tom Ledoux and Superintendent Dr. Patrick Daly and (at right) NRHS Principal AJ Loprete and mathematics teacher Derek Dorval. (Courtesy Photo)

 

NORTH READING — Sucheta Srikanth, a junior at North Reading High School, has won first place in the 2024 National Data Science Competition.

The competition challenge was to create an Artificial Intelligence (AI)/Machine Learning (ML) model to analyze a dataset to predict the “college happiness score” as accurately as possible, while providing an effective explanation of the methodology used.

As prospective students navigate their higher education options, understanding the value and satisfaction a college provides is crucial. Leveraging data from the College Scorecard Database, Forbes Rankings, HappyScore Data, Crime Data, Undergraduate Enrollment figures, and insights from Columbia University’s Advanced Data Analysis Course, students were asked to create models to gauge university life quality using any subset of combination of features provided in the dataset. They had to factor in what makes a college environment not just survivable, but enjoyable, and predict how various institutions rank on the happiness scale. Participants had to build a ML model and train it on the provided data set and then select what they believed are key attributes that contribute to the happiness score using statistical methods.

Said Srikanth, “I have always been fascinated by human behavior and I am going to attend college in a year and so the competition was intriguing. I know how to program and am learning how ML models work and when Mr. Ledoux posted this competition just before winter break, I thought I would give it a try.”

She chose statistical methods to select her key attributes that had the best correlation and then used regression to fit the test data to her ML model to make her winning prediction. “I am glad to see students like Suchi take advantage of multiple pathways we offer in our curriculum and use it to pursue their passions,” said NRHS Principal Anthony Loprete.

Srikanth’s winning entry was written in Python, a computer programming language commonly used in AI/ML, and the competition judges noted, “We were extremely impressed by the accuracy of your prediction model.”

NRHS physics teacher Tom Ledoux was pleased as well. “I got an email about the competition and posted it to all my classes. I am glad that Suchi ran with it,” he said.

Added NRHS mathematics teacher and Curriculum Leader Derek Dorval, “I helped Suchi with the basic concept of fitting a model and assessing that fit in her AP Statistics class, but this is really her model and she deserves all the credit!”

“Artificial intelligence and machine learning will play a role in all of the careers and daily tasks that our students will encounter in the future,” noted Superintendent of Schools Dr. Patrick Daly. “It is wonderful to see Suchi learning to master the skills needed to create these models and to gain national recognition for her interdisciplinary project.”

The 2024 National High School Data Science Competition is jointly sponsored by VeritasAI and the Harvard University Open Data Project. The competition is open to any high schooler worldwide.