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
Predecimos cuánto venderá cada producto la próxima temporada utilizando sus imágenes, atributos y datos históricos, generando recomendaciones de producción precisas y accionables.
We want to go the route of deeper understanding of the database combined with our knowledge in diferent types of models to obtain a model that should by its own nature work with the data we have.
A webpage where the user can see how our LightGBM predicts, and a very detailed explainability section.
Sistema inteligente de predicción y análisis de oportunidades comerciales para optimizar estrategias de ventas.
Ding Dong: ML pipeline para predecir demanda de 2,250 productos Mango. K-Fold + 32 features (embeddings, temporales, distribución).
No time
This is our project. We are very proud.
n
Snake Trainers prediu amb 85% de precisió quins usuaris gastaran en 7 dies analitzant només el primer dia. Processem 20M instal·lacions en minuts i permetem optimitzar campanyes en temps real.
A simple and user-friendly interface to understand complex models and statistical explanations.
We present SAILES, an LLM-powered assistant designed to provide transparent, explainable insights into a model's prediction of whether an opportunity will be Won or Lost
Hemos desarrollado un sistema de machine learning que predice con precisión el comportamiento del cliente mediante división de datasets para entrenamiento y validación robustos.
data
Opportunity XplAIn is an AI-powered tool that predicts whether a customer is likely to be profitable based on their past interactions with the company.
Machine Learning Explainability, our solution to all your questions about past and future opportunity sales.
We trained a model on previous data to determine whether an opportunity will be won or lost and applied various explainability techniques to explain why the model predicted this.
In this project we developed a ML model which predicts a binary output.
Highly performant two stage GBDT student models distilled from ODMN teacher model.
This project provides a smart tool that helps sales teams understand why a business opportunity is likely to be won or lost.
pepito
Schneider, Random Trees, Shapley Values
After training and comparing 5 different tools, our model based on Random Forest Classifier predicts Schneider's sales with a 0.83 F1 score and points to customer hitrate as the most important factor.
Datathon 2025
Fast, simple LightGBM pipeline to predict 7-day in-app revenue and rank high-value users in milliseconds.
1 – 24 of 57
