Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Predict the Wrecks, Plunder the Past!
Using data for formulate the perfect recipe for your future coffee shop endeavors
A image classification hybrid machine learning model to detect melanoma.
Driven to Drive: Powering Uber’s Growth Through Smarter Onboarding
Effortless navigation, data-driven direction.
Our team used Uber signup data to predict which drivers would complete their first trip. XGBoost (99.8% accuracy) showed referrals, quick background checks, and early vehicle adds as key predictors.
Stopping cancer one spot at a time
Analyzed Uber driver signups to identify factors determining whether a driver ends up completing their first ride.
AI-powered location intelligence for high-rating business success
Who Signs Up.. and Who Actually Drives? Using a StrataScratch dataset, we predict driver activation using data visual and supervised learning. From click to ignition—what turns a signup into a driver?
We've created an AI music snippet generator! We first isolate lyrics from melody, then generate AI celebrity voice and lyrics, then transpose the desired celebrity voice onto the new snippet.
Intelligent Route Optimization for Emergency & Disaster Response | Melissa Data Challenge
Optimize risk-benefit analysis for Uber drivers with our data analysis models. Our product is an impactful tool to research specific driver signup metrics for both drivers and the company.
Analyze AI-generated responses by engineering linguistic features, readability, and semantic similarity to predict winning models and improve prompt-response interaction quality.
Pursuing Fair and Accurate Skin Lesion Diagnosis Using Deep Learning
Just snap a photo—our app will tell you the dog’s breed! BreedFinder combines deep learning and a clean iOS mobile interface to classify 70 dog breeds using a diverse Kaggle dataset.
We built a model to predict which Uber driver signups will take their first trip, helping optimize onboarding and boost early driver activation.
We worked to identify trends in the images and metadata of benign and malignant skin cancer results. From there, we used a CNN to train with data and attempt to automate the identification of cancer.
What if Uber could predict which signups will actually start driving? Our project explores this question using real data to uncover key factors behind driver activation!!
ChatGPT-4o's AI Studio Ghibli filter returns an cartoon image of the user…seems fun, right? However, this project analyzes the consequences of AI social media trend usage to carbon emissions.
We developed a machine learning model to determine users' preferences to AI-generated response
We will explore how we used this data to compare and conclude new driver commit rate using visuals and a logistic regression model
More Drivers More Cash
https://speedfast-xi.vercel.app/
1 – 24 of 48
