A framework to improve churn prediction performance in retail banking

Financial Innovation

Table 2 Original features

01. Adjusted overdraft limit [real]	17. Overdraft limit [real]
02. Balance value (inflow-outflow) of credit portability [real]	18. Paycheck value [real]
03. Balance value (inflow-outflow) of salary portability [real]	19. Professional profile [cat]
04. Category of the customer's bank agency [cat]	20. Savings account balance [real]
05. Checking account balance [real]	21. Segment (Method A) [cat]
06. Cohort [int]	22. Segment (Method B) [cat]
07. Credit card limit [real]	23. The region where the customer's bank agency is located [cat]
08. Credit score categorical [cat]	24. Type of credit portability [cat]
09. Credit score continuous [real]	25. Type of salary portability [cat]
10. Digital maturity [cat]	26. Value customer takes the credit value in the banking system [real]
11. Education level [cat]	27. Value of inflow of credit portability [real]
12. Gender [cat]	28. Value of inflow of salary portability [real]
13. Marital status [cat]	29. Value of outflow of credit portability [real]
14. Maximum viable overdraft limit [real]	30. Whether the customer has received a salary with the bank [bin]
15. Overall income [real]	31. Whether the customer is a civil servant [bin]
16. Overall overdraft limit [real]	32. Whether the customer is an employee in the company [bin]

Binary features \(\left[\mathrm{bin}\right] \in \{0, 1\}\); real features \(\left[\mathrm{real}\right]\in {R}\); integer non-negatives features \(\left[\mathrm{int}\right]\in {Z}^{+}\); and categorical features [cat]