Title :
Cross-Channel Customer Mapping
Author :
Basak, Jayanta ; Goyal, Sunil
Author_Institution :
IBM India Res. Lab., Delhi
Abstract :
In multi-channel setting (for example, Web channel and storefront), one often is required to generate an integrated view of customers across channels for making better CRM, marketing and merchandizing decisions. It is essential to identify a customer uniquely across channels to generate an integrated customer view. It is often not feasible to impose a unique identifier on a customer across channels. Moreover, a customer may not provide true demographic information, making it even more difficult to track. In the absence of a unique identifier and correct demographic information, the behavioral signature of a customer can perhaps be used to track customer across channels (cross-channel customer mapping) where behavioral signature comprises of the channel-independent behavioral characteristics. We define certain channel-independent behavioral characteristics that are easily computable and adaptable with incremental information gain. We then provide algorithms to match behavioral signatures across channels. We demonstrate our methodology using ´safeway´ data, where we achieved significant accuracy, for example, over 90% for the high value customers.
Keywords :
behavioural sciences; customer relationship management; data mining; demography; behavioral signature; channel-independent behavioral characteristics; cross-channel customer mapping; data mining; demographic information; safeway data; Data analysis; Data mining; Demography; Information science; Learning; Testing; Applications; Data Mining; E-Commerce; Knowledge Discovery;
Conference_Titel :
Computer and Information Science, 2008. ICIS 08. Seventh IEEE/ACIS International Conference on
Conference_Location :
Portland, OR
Print_ISBN :
978-0-7695-3131-1
DOI :
10.1109/ICIS.2008.87