Here are other challenges i've made. You can also find those public kernels on my kaggle's profile.
DATA SCIENCE
Solar Power Generation in Europe : Kaggle part 1 - 2 - 3 - Notebook part 1 - 2 - 3
Use case: countries segmentation depending on their generation profile, power plant's efficiency prediction accross time
Data: hourly estimates of an area's energy potential for 1986-2015 as a percentage of a power plant's maximum output
Concepts: unsupervised ML (KMeans Clustering), basics statistics for the exploratory data analysi, other supervised M.L classical models, use of Facebook's lib prophet for time series, deep learning : R.N.N and more.
Cirta - Particle Type Classification : part 1 - part 2
Use case: The goal is to build a machine learning model to help physicists identify particles in images
Data: images after particles collisions.
Concepts: an imbalanced multiclass target, over & undersampling, ensemble & gradient boosting models, M.L.P...