Hello and good afternoon, Regarding the Loan dataset for the credit risk course.
That particular dataset is very different on the Kaggle page currently and contains no Ids and members Ids.
It also contains 2M+ rows of data instead of 400K+ you show on the videos.
Thank you Spiros Mouratis
We have divided the dataset into two – until 2014 and 2015 onwards. The one we use in the lectures is only the first half of the dataset.
The reason for that is that later on we give the rest for homework. If you split the original kaggle dataset in this way, you’d reach our datasets.
Finally, please find all datasets that we use here: https://www.dropbox.com/sh/6cc01fcljk457gd/AADD_MJFfVcE5VR3UzlKDATla?dl=0