Hi All,
I am working on developing a credit risk model using IFRS Regulations. So I have prepared the data and my first step is to find the probability of default for next 24 months using logistic regression. How do we actually get the probability of default for next 24 months for all the account ids.
And also it will be of great help if some one can share me/ guide me how to build credit risk model in Alteryx with IFRS Regulations and find the 1) Probability of Default 2) Loss Given Default 3) Exposure at Default 4) Credit Score
I am sharing you a sample dataset.
Kindly help me in developing me a workflow for finding the above.
IS_DEFAULT : It is the target column and rest of the other columns are independent columns
| ACCT_ID | LOAN_START_DATE | CURRENT_MONTH | MONTH_ON_BOOK | LOAN_TENURE | AGE | YEAR_SINCE_CUSTOMER | DISBURSED_LIMIT | GDP | INFLATION_RATE | UNEMPLOYMENT_RATE | TIME_TO_DEFAULT | IS_DEFAULT |
| -1936469 | 01-07-2017 | Jan-18 | 6 | 29 | 39 | 0 | 5000000 | 4.6 | 3.7 | 2.3 | 0 | 0 |
| -1936469 | 01-07-2017 | Feb-18 | 7 | 29 | 39 | 0 | 5000000 | 4.6 | 3.7 | 2.3 | 1 | 1 |
| -1962960 | 01-02-2017 | Jan-18 | 11 | 35 | 38 | 0 | 300000 | 3.1 | 5.6 | 2.5 | 0 | 0 |
| -1962960 | 01-02-2017 | Feb-18 | 12 | 35 | 38 | 0 | 300000 | 3.1 | 5.6 | 2.5 | 1 | 1 |
| -1964468 | 01-02-2017 | Jan-18 | 11 | 29 | 32 | 2 | 13932 | 3.1 | 5.6 | 2.5 | 0 | 0 |
| -1964468 | 01-02-2017 | Feb-18 | 12 | 29 | 32 | 2 | 13932 | 3.1 | 5.6 | 2.5 | 1 | 0 |
| -1964468 | 01-02-2017 | Mar-18 | 13 | 29 | 32 | 2 | 13932 | 3.8 | 4.8 | 2.4 | 2 | 0 |
| -1964468 | 01-02-2017 | Apr-18 | 14 | 29 | 32 | 2 | 13932 | 3.8 | 4.8 | 2.4 | 3 | 0 |
| -1964468 | 01-02-2017 | May-18 | 15 | 29 | 32 | 2 | 13932 | 3.8 | 4.8 | 2.4 | 4 | 0 |
| -1964468 | 01-02-2017 | Jun-18 | 16 | 29 | 32 | 2 | 13932 | 4.6 | 3.7 | 2.3 | 5 | 0 |
| -1964468 | 01-02-2017 | Jul-18 | 17 | 29 | 32 | 2 | 13932 | 4.6 | 3.7 | 2.3 | 6 | 0 |
| -1964468 | 01-02-2017 | Aug-18 | 18 | 29 | 32 | 2 | 13932 | 4.6 | 3.7 | 2.3 | 7 | 0 |
| -1965350 | 01-02-2017 | Jan-18 | 11 | 29 | 25 | 1 | 27844 | 3.1 | 5.6 | 2.5 | 0 | 0 |
| -1965350 | 01-02-2017 | Feb-18 | 12 | 29 | 25 | 1 | 27844 | 3.1 | 5.6 | 2.5 | 1 | 0 |
| -1965350 | 01-02-2017 | Mar-18 | 13 | 29 | 25 | 1 | 27844 | 3.8 | 4.8 | 2.4 | 2 | 0 |
| -1965350 | 01-02-2017 | Apr-18 | 14 | 29 | 25 | 1 | 27844 | 3.8 | 4.8 | 2.4 | 3 | 0 |
| -1965350 | 01-02-2017 | May-18 | 15 | 29 | 25 | 1 | 27844 | 3.8 | 4.8 | 2.4 | 4 | 0 |
| -1965350 | 01-02-2017 | Jun-18 | 16 | 29 | 25 | 1 | 27844 | 4.6 | 3.7 | 2.3 | 5 | 0 |
| -1965350 | 01-02-2017 | Jul-18 | 17 | 29 | 25 | 1 | 27844 | 4.6 | 3.7 | 2.3 | 6 | 0 |
| -1965350 | 01-02-2017 | Aug-18 | 18 | 29 | 25 | 1 | 27844 | 4.6 | 3.7 | 2.3 | 7 | 0 |
| -1965350 | 01-02-2017 | Sep-18 | 19 | 29 | 25 | 1 | 27844 | 5.8 | 2.9 | 2.4 | 8 | 0 |
| -1965350 | 01-02-2017 | Oct-18 | 20 | 29 | 25 | 1 | 27844 | 5.8 | 2.9 | 2.4 | 9 | 0 |
| -1965700 | 01-02-2017 | Jan-18 | 11 | 119 | 52 | 6 | 750150.93 | 3.1 | 5.6 | 2.5 | 0 | 0 |
Thanks,
Karthik.
