Please see my solution on https://github.com/denizstij/Landslide-Prevention-and-Innovation-Challenge. which utilize LightGBM and many derived features. I had no... See more

I used CNN.Nice idea, the 5x5 forms a spatial grid and the various features are channels in that grid. Makes a lot of sense, but also lots of hard work. Unlike... See more

Hello everyone👋Thanks to everyone who made this competition possible, Hong Kong University for providing the data, Zindi for hosting it, and to all the competi... See more

Hi, nice comp, glad it is over.Congratulations to the winners. If I remember correctly, Babawale was leading for a long time (and by far) so it is good that he... See more

Hello everyone👋 and Congrats to the winners.Here is my solution link. It is an ensemble of XGB and LightGBM trained on 10 stratified folds with oversampling me... See more

Here is the link for the solution.Please Leave a🌟 to my repo, if you find it useful🙏

use this ensembling method to improve your score::GIST::/JONNY-ME/197b992139df0af1229d2505bfc9bf6f

So I wrote an article using data from this competition. Read and share. ✨ https://saheedniyi.hashnode.dev/handling-imbalanced-datasets-tuning-classification-thr... See more

Hi All,I have been wondering if anybody is happy to share some thoughts around what they did/are doing regarding data cleaning/preparation.I know that this may... See more

I've just published a basic EDA at https://www.kaggle.com/code/denizstij/eda-landslide-prevention-and-innovation/notebook

Hi,I am a real beginner here so please excuse the question!I am trying to run the starter notebook in Colab and I get an error when I get to this line:pp = pd.r... See more