CSV File Description
The Data folder contains the following data:
- Loan.csv and Borrower.csv: data sets with 100K rows of the simulated data used to build the end-to-end Loan Credit Risk solution.
- Loan_Prod.csv and Borrower_Prod.csv: data sets with about 20 rows of the simulated data used in the Production pipeline.
Loan.csv and Loan_Prod.csv contain the following fields:
| Field | Type | Description |
|---|---|---|
| loanId | Integer | Unique Id of the loan |
| memberId | Integer | Unique Id of the borrower |
| date | Date | a) Historical data: the loan approval date b) Production data: the loan application date. Format: M/D/YYYY (e.g. 3/9/2016, 3/13/2016) |
| purpose | String | Purpose of the loan e.g., debtconsolidation |
| isJointApplication | String | Flag about the nature of the application (joint or individual) |
| loanAmount | Float | Total amount to be borrowed |
| term | String | Number of months of payments on the loan e.g., 36 months |
| interestRate | String | Interest Rate on the loan e.g., 7.21 % |
| monthlyPayment | Float | Monthly payment owed by the borrower |
| grade | String | Loan grade (risk-related) e.g. A2 |
| loanStatus | String | Status of the loan (Label) Values taken: Current, Charged Off (This field is not present in the Loan_Prod.csv file) |
Borrower.csv and Borrower_Prod.csv contain the following fields:
| Field | Type | Description |
|---|---|---|
| memberId | Integer | Unique Id of the borrower |
| residentialState | String | Residential state of the borrower e.g., MA |
| yearsEmployment | String | Number of years of employment of the borrower e.g., 10+ years |
| homeOwnership | String | Home ownership status of the borrower Values taken: own, rent, mortgage |
| annualIncome | Float | Annual income of the borrower |
| incomeVerified | String | Flag indicating if the income was verified or not |
| dtiRatio | Float | Debt to income ratio: borrower’s total monthly debt payments (without mortgage and the requested loan) divided by the monthly income. It is expressed in percentage |
| lengthCreditHistory | Integer | Length of the credit history in terms of years |
| numTotalCreditLines | Integer | Total number of credit lines in the borrower's credit file |
| numOpenCreditLines | Integer | Number of open credit lines in the borrower's credit file |
| numOpenCreditLines1Year | Integer | Number of credit lines in the borrower's credit file that were opened in the past year |
| revolvingBalance | Float | Total credit revolving balance |
| revolvingUtilizationRate | Float | Amount of credit the borrower is using relative to all available revolving credit e.g., 7.30% |
| numDerogatoryRec | Integer | Number of derogatory public records (includes tax liens, bankruptcies, and other judgements such as civil lawsuits) |
| numDelinquency2Years | Integer | Number of 30+ days past-due incidences of delinquency in the borrower's credit file for the past 2 years |
| numChargeoff1year | Integer | Number of charge-offs within 1 year |
| numInquiries6Mon | Integer | Number of inquiries in past 6 months |
