Exploring and Preparing Loan Data
Expected Loss
- Probability of Default (PD)
- Exposure at Default (EAD)
- Loss Given Default (LGD)
expected_loss = PD * EAD * LGD
Data Columns
- Mix of behavioral and application data is required
- Contain columns simulating credit bureau data
| Column |
Column |
| Income |
Loan Grade |
| Age |
Loan Amount |
| Home Ownership |
Interest Rate |
| Employment Length |
Loan Status |
| Loan Intent |
Historical Default |
| Percent Income |
Credit Length History |
Exploring with Cross Tables
pd.crosstab(cr_loan['person_home_ownbership'], cr_loan['loan_status'],
values=cr_loan['loan_int_rate'], aggfunc='mean').round(2)
Exploring with Visuals
plt.scatter(cr_loan['personal_income'], cr_loan['loan_int_rate'], c='blue', alpha=0.5)
plt.xlabel("Personal Income")
plt.ylabel("Loan Interest Rate")
plt.show()
Dropping Outlier in One Line
cr_loan_new = cr_loan.drop(cr_loan[cr_loan['person_emp_length'] > 60].index)
Print Null Value Column Array