The Mining Data Mart - Data Mining Techniques in CRM: Inside Customer Segmentation - page 182

Table 4.31 The transactions table.

Field name Field type Field description

Year_Month Int The number that indicates the year and

month of data

Customer_ID Int Customer ID or loyalty card ID

Store_Code Int The code of the store where the trans-

action took place (also includes the
channel information, in case of an
Internet or phone order)

Morning_Transactions Int Number of transactions made from 08:00 to

17:00

Weekend_Transactions Int Number of transactions on Saturdays and

Sundays

Num_of_Transactions Int Total number of transactions/visits

Num_of_Items Int Total number of items purchased

Total_Paid_Amount Real Total amount paid

Date_Last_Transaction Datetime The date and time of the last (most recent)

transaction within the specific month

Year_Month, Customer_ID, and Store_Code are the primary keys (PKs) of this table.

Monitoring Key Usage Attributes on a More Frequent Basis

According to the requirements of each organization, a specific subset of key
usage attributes could be monitored by weekly or even daily aggregations.
Especially for retailers, the daily purchases should bemonitored carefully
in order to investigate seasonal and market event effects. A ''diary'' lookup
table can be used to map dates with special occasions, such as sales seasons,
holidays, weekends, and so on.

Purchases by Product Groups

The next monthly table (''M_Purchases''), Table 4.32, records the relative spending
of each customer by product groups. The product level selected for this aggregated