Cross Channel Customer Mapping

In multi-channel setting (for example, web channel and storefront), it is often required to generate an integrated view of a customer across channels for making better CRM, marketing and merchandizing decisions. In order to generate integrated view, it is essential to uniquely identify a customer across channels. Due to various reasons, it is often not feasible to impose a unique identifier on a customer across channels. Moreover, a customer may not provide her true demographic information, which makes it even more difficult to track her. In the absence of a unique identifier and the demographic information, the behavioral profile of a customer can perhaps be used for tracking her across channels (cross-channel customer mapping). We define four channel-independent behavioral attributes namely, brand loyalty, price preference, responsiveness to promotion, and spending range. We call a behavioral attribute of a customer to be channel-independent if it does not change substantially with the channel characteristics in absence of a conscious effort from the customer. We defined the attributes in such a way that they reflect the statistical nature of a customer behavior, are easily computable, and can be incrementally updated over time. We then match these profile attribute values across channels to map the customers. We used two months Safeway transaction data; randomly divided it into two channels in different proportions, and computed these attribute values. We achieved significant accuracy in tracking the customers across channels, for example, more than 90% accuracy for the high valued customers.

By: Jayanta Basak, Sunil Goyal

Published in: RI06004 in 2006


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to .