The goal of this competition is to predict which clients are more likely to default on their loans. The evaluation will favor solutions that are stable over time.
- Create a folder
data
with the parquet files from the Kaggle competition - Create a virtualenv
venv
(or whatever name you want but remember to add it to the gitignore!) - Run
pip install -r requirements.txt
- Notebooks are stored in the
notebooks
folder, currently exploring the dataset. - Insights, questions, and granular todo's are currently stored in the
doc
folder. src
contains useful functions to be used in all notebooks. This is done to improve code versioning.
Repo setup- Explore datasets and gather insights in the
doc
folder