Places to find credit risk data-sets

Question

I am looking for places to get datasets regarding credit risk and risk analytics in financials services.

I have tried many places but was unable find what I am looking for. Can I get any pointer or link to find these?

Answer 1

The Lending Club dataset might be fun for you to play around with:

https://www.lendingclub.com/info/download-data.action

Answer 2

Have you tried https://www.kaggle.com/datasets? There is a credit card fraud detection databse available on this site.

Answer 3

Try to use an automatic feature search for ML modeling: https://github.com/upgini/#-data-coverage-and-statistics-updated-20220525

Work through python:

import pandas as pd
from upgini import FeaturesEnricher, SearchKey

# load labeled training dataset to initiate search
train_df = pd.read_csv("customer_loan_prediction_train.csv")
X = train_df.drop(columns="fraud_flag")
y = train_df["fraud_flag"]

# now we're going to create `FeaturesEnricher` class
enricher = FeaturesEnricher(search_keys={"IP_address": SearchKey.IP,
"phone_number": SearchKey.PHONE, "Date": SearchKey.DATE,
})


# everything is ready to fit! 
enricher.fit(X, y)