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
We use more general feature selection, more modern classifiers, training set supersampling, and grid-search hyperparameter optimization in order to give better predictors of CM differentiation
Optimized through advanced feature selection & class imbalance handling. Achieving 83% accuracy with XGBoost
Using SequentialFeatureSelection with boosting algorithms to accurately predict stem cell content in bioprocess.
Use of Inhibition percentage to get better results
With a combination of RandomForestClassifier, LogisticRegressor, KNN and GradientBoostClassifier with a Randomized Search (with cross-validations) to optimise hyperparamaters: Accuracy of 0.8333
Improving existing drug screening models by using a combination of 4 ML models
MyFoodPal: Empower your gut health journey with personalized IBS symptom tracking, food analysis, and dietary recommendations. Your path to a happier gut starts here!
We achieved spearman correlation of 0.0012 pvalue!
\ In our attempt, we focused on challenge 0, and attempted accurate prediction of CM content (sufficient vs insufficient).
Through 5 machine learning models, we have determined that the best way of solving any problem is to brute force every classification model that we know! (fun stuff :)
We tackled Challenge 0. We trained our Random Forest Classifier model to be able to predict insufficienct vs. sufficienct cardiomyocyte content with a 89% accuracy.
This project uses XGBoost learning to model the relationships between anonymous food groups and their effect of provoking gastrointestinal symptoms for a small sample of 50 individuals.
1 – 12 of 12
