Welcome to Data Snax Datathon 2026!

Culminate STL TechWeek at DataSnax’s 2nd annual Datathon on April 18th at the University of Health Sciences and Pharmacy in St. Louis
On April 18th from 2-6 pm, join us for a collaborative competition where participants will work in teams to solve real-world, data-driven challenges. It’s a great chance to sharpen your skills, learn from others, and have fun tackling problems together.
For questions or assistance with the application, contact:
📧 danniel.franco@uhsp.edu
📞 (314) 267-3051
Data Snax is here to welcome students interested in data and computer science. Our goal is to connect you with opportunities to explore, engage, and grow through hands-on activities and campus resources
 

Requirements

What to Build

Participants should build a machine learning solution using the provided dataset. Teams are expected to explore the data, identify useful patterns, and develop models that address the challenge.

During the process, participants should:

  • Select relevant features from the dataset

  • Optionally transform or engineer features when appropriate

  • Explore patterns in the data

  • Create visualizations such as boxplots, scatter plots, or heatmaps

  • Train machine learning models

  • Record key model training parameters

  • Compare at least two machine learning approaches

  • Evaluate model performance using appropriate metrics

The goal is to demonstrate thoughtful data exploration, model development, and clear communication of results.

What to Submit

Each team must submit the following on Devpost:

  • A runnable notebook (such as a Jupyter or Google Colab notebook) containing the code used for data exploration and model training

  • A short report summarizing the approach, findings, visualizations, and model performance

  • Clear documentation of the models tested and their evaluation metrics

Submissions should allow judges to understand your workflow, reasoning, and final results.

 

Hackathon Sponsors

Prizes

$375+ in prizes
+ other prizes
Best Use of Gemini API
1 winner

Google Swag

It’s time to push the boundaries of what's possible with AI using Google Gemini. Check out the Gemini API to build AI-powered apps that make your friends say WHOA. So, what can Gemini do for your hackathon project?

Understand language like a human and build a chatbot that gives personalized advice

Analyze info like a supercomputer and create an app that summarizes complex research papers

Generate creative content like code, scripts, music, and more

Think of the possibilities… what will you build with the Google Gemini API this weekend?

Gift Card 1st Place Open
$150 in cash
1 winner

Gift Card 1s Place College
$125 in cash
1 winner

Gift Card 1st Place High School
$100 in cash
1 winner

Devpost Achievements

Submitting to this hackathon could earn you:

Judges

Sylvester Orimaye

Sylvester Orimaye
Assistant Professor, Health Data Science and Program Director

Danniel Franco

Danniel Franco
Double Major Student in Computer Science and Data Science

Christian Hardwood

Christian Hardwood
Double Major Student in Computer Science and Data Science

Brayden Daley

Brayden Daley
Major Student in Data Science

Schylar Srey

Schylar Srey
Double Major Student in Computer Science and Data Science

Judging Criteria

  • Feature Selection
    Teams should demonstrate thoughtful selection of relevant features from the dataset. Judges will look for evidence that participants explored the data and identified variables that meaningfully contribute to the model’s performance.
  • Pattern Identification
    Participants are encouraged to explore the dataset and identify patterns, relationships, or trends that help explain the problem. Strong projects will show curiosity in understanding the data before modeling.
  • Data Visualization
    Effective visualizations such as boxplots, scatter plots, or heatmaps should be used to explore and communicate insights from the data. Visualizations should help support the analysis and make findings easier to understand.
  • Machine Learning Model
    Teams should train at least one machine learning model to address the challenge. Judges will evaluate whether the chosen approach is reasonable and appropriately applied to the dataset.
  • Training Parameters
    Projects should document key training parameters and modeling decisions. This helps demonstrate transparency and allows others to understand how the model was developed.
  • Model Comparison
    Teams should compare at least two machine learning models or approaches to evaluate performance differences and justify their final choice.
  • Report Summary
    Each team should provide a clear summary explaining the problem, the approach taken, and the main conclusions of the project.
  • Visualizations in Report
    The report should include relevant visualizations that support the analysis and help communicate insights effectively.
  • Performance Metrics
    Teams should include performance metrics that evaluate how well their model performs and explain what those results mean.
  • Model Performance (AUC)
    Models will be evaluated based on their AUC score, with values above 85% indicating strong predictive performance.

Questions? Email the hackathon manager

Tell your friends

Hackathon sponsors

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.