Winter Hackathon 2025 – Team DataDivas (DataCamp Donates Scholars)
DataDivas team members Ann Lam, Jasmin Rafi, and Vicky Yan entered WiBD Winter Hackathon following their successful completion of WiBD’s transformative education and professional development program through Datacamp Donates, a program designed to equip motivated candidates with essential data science competencies through the Datacamp learning platform.
They were mentored by industry experts Ravi Condamoor and Srividhya Chandrasekaran throughout the challenge.
On May 23rd, WiBD successfully concluded its Winter Hackathon under the leadership of WiBD Global Hackathon Director Rupa Gangatirkar and Technical Advisor Stuti Patel.
The Winter Hackathon Challenge 2025
This year’s competition was powered by the WiDS Datathon Global Challenge and developed in partnership with the Ann S. Bowers Women’s Brain Health Initiative (WBHI), in collaboration with Cornell University and UC Santa Barbara. The Healthy Brain Network (HBN), the flagship scientific initiative of the Child Mind Institute, along with the Reproducible Brain Charts project (RBC), provided essential datasets and technical support for the competition.
Hosted on the Kaggle platform, the hackathon centered on the theme “Unraveling Mysteries of the Female Brain,” with participants focusing on analyzing women’s brain health data specifically for advancing early ADHD detection and diagnostic capabilities.
Participants worked with comprehensive training datasets encompassing patients’ socio-demographic information, emotional and behavioral assessment scores, and fMRI (Functional Magnetic Resonance Imaging) data, which measures minute blood flow variations corresponding to brain activity patterns. The primary objective required teams to develop predictive models capable of determining both gender classification and ADHD diagnostic status based on the provided multimodal datasets.
Team Testimonial and Journey
The experience at the WiBD Winter Hackathon 2025 provided an exceptional opportunity to apply and expand our data science capabilities developed through the Datacamp Donates initiative. The hackathon presented the perfect balance of challenge and engagement, allowing us to implement Python programming skills across the entire data science pipeline – from initial data cleaning and processing through exploratory data analysis to advanced machine learning model development and optimization.
As a DataCamp Donates team, all of our members were relatively new to the fields of data and Machine Learning, although some had prior experience in coding. DataCamp provided all the courses necessary for mastering Data Analysis and Machine Learning skills, significantly accelerating our learning during the 8-week hackathon. The topics ranged from data cleaning and feature engineering to Machine Learning in Python and MLOps.
The journey from raw data to predictive models was both technically challenging and intellectually rewarding. We successfully navigated data preprocessing challenges, extracted meaningful insights through analysis, and progressed to implementing various machine learning algorithms to predict target variables. The hyperparameter tuning process further enhanced our understanding of model optimization and performance improvement.
Our mentor, Ravi Condamoor demonstrated exceptional mentoring expertise, delivering precisely the right depth of knowledge and guidance for machine learning newcomers. His approach was perfectly calibrated – providing comprehensive support without creating information overload, enabling us to overcome technical obstacles while building genuine understanding. Ravi helped fill in the gaps by providing background knowledge and insights into the inequality present in female healthcare research, and how machine learning models can be used to bridge the diagnostic gap caused by the lack of female medical data.
Meanwhile our second mentor, Srividhya Chandrasekaran proved instrumental in maintaining project momentum and ensuring timely milestone completion through effective project management.
This collaborative learning environment fostered both technical growth and professional development. The combination of hands-on problem-solving, peer collaboration, and expert mentorship created an ideal framework for skill application and knowledge consolidation.
Our team was diverse and multi-disciplinary. Coming from different areas of study and global background, based in Australia and the United States. We all made an effort to keep up and communicate effectively. Using online collaborative tools like Google Colab, Slack, and Google Meet, we were able to share our progress through weekly meetings and constant communication. The steady improvement on the Kaggle leaderboard was proof of our progress and encouraged us to continue trying new approaches.
Despite being first-time participants in a Kaggle competition, we were able to publish our findings based on real-world scenarios, and we left the experience motivated to continue our journey in data science.
We extend our sincere gratitude to WiBD for orchestrating this transformative learning experience and providing a platform that seamlessly bridges theoretical knowledge with practical implementation in Data Science and Machine Learning.
