The Mining Data Mart - Data Mining Techniques in CRM: Inside Customer Segmentation - page 148

Table 4.11 An indicative grouping hierarchy of transactions according to their type in
retail banking.

Transaction type Transaction group Transaction subgroup

Deposits

• Deposit internal
• Deposit external

• Deposit internal
• Deposit external

Credit cards

• Cash advance
• Purchases

• Cash advance
• One-off purchases
• New installments (installment due to a
new purchase)
• Old installments (installment due to an
old purchase)

Withdrawals

• Withdrawal classic
• Withdrawal overdraft

• Withdrawal classic
• Withdrawal overdraft

Payments

• Banking payment • Home loan payment

• Business loan payment
• Consumer loan payment
• Credit card payment
• Insurance payment

• Bill payment • Public service payment

• Telecommunication services payment
• Internet services payment
• Pay TV services payment
• Other payment

Transfers

• Transfer internal
• Transfer external

• Transfer internal
• Transfer external

Queries •Queries •Queries

THE CUSTOMER ''SIGNATURE'' - FROM THE MINING DATA MART
TO THE MARKETING CUSTOMER INFORMATION FILE

Most data mining applications require a one-dimensional flat table, typically at the
customer level. Therefore, analysts should move one step beyond, since even the
data mart tables are not immediately ready for mining. A recommended approach
is to consolidate the mining data mart information into one table which should
be designed to cover the key mining as well as marketing and reporting needs.
This table, also referred to as the marketing customer information file or MCIF,
should integrate all the important customer information, including demographics,
usage, and revenue data, thus providing a customer ''signature'': a unified view
of the customer. Through extensive data processing, the data retrieved from the