Behind the scenes: A customer experience powered by Adobe Experience Platform

In the previous video we saw how an example brand, Luma, was able to create a rich, rewarding and relevant customer experience. This video looks at how Adobe Experience Platform is used to accomplish this journey.

Transcript
In the previous video, we saw how Luma was able to create a rich, rewarding and relevant journey for a customer named Sarah. This video will look at how Adobe Experience Platform is used to accomplish this journey. Experience Platform brings multiple data streams together to fill real time customer profiles, to deliver experiences powered by continuous intelligence. In this example, we’re using data from multiple sources, first from Luma’s website and mobile app captured by Adobe Analytics and available in Experience Platform. Next, Luma’s Studio management system which sends periodic updates through batch ingestion. Finally, Luma’s loyalty system that connects in real time through streaming ingestion. We’ll examine how this works by looking at the data flow for Luma’s loyalty system. The structure of Luma’s loyalty data is expressed by a schema using building blocks from Experience data model. This schema describes the logical meaning of the data. It also contains information for the identities used in this data set used to build the identity graph. In this case, the loyalty ID is used as a primary identifier while an email address and phone number are used as secondary identifiers. Data sets are at the heart of Adobe Experience Platform. They represent the streams of data coming into and going out of Experience Platform. Batches represent individual data processing jobs. Here, new data points of loyalty data are streaming into Experience Platform. The data is stored in the Experience Platform data lake and can be used to build a real time customer profile. Machine learning analysis and cross channel queries can be run on top of the data. Data coming from different sources can be seen as fragments of real time customer profiles. These fragments represent a consumer and his or her corresponding behavior across channels such as web, mobile, retail and in Sarah’s case, lessons that she attended. When Sarah adds a product to the shopping cart, that behavior is captured by Adobe Analytics and added into a real time customer profile in Experience Platform. In the background, an identity graph is built using identity information available in the data. In Sarah’s case, she has several individual identities that are linked deterministically, her Experience cloud IDs representing her web visits and mobile device, Luma membership ID, phone number and email. These identities are tied together in the identity graph. Let’s look at how real time customer profiles are used. Remember, when Sarah registered with a Luma Studio host, she presented the barcode on her mobile device representing her membership ID matching the data in the CRM system. The studio system integrated with Experience Platform performs a lookup for her customer profile using her membership ID. Sarah’s real time customer profile is created on the fly by using the identity graph to merge together individual profile fragments from various data sources. As a result, the studio host can see Sarah’s recent activities and the fact that she has shown interest in clothing. Segments can be used to personalize content. In this case, Luma has defined a segment, online shoppers as membership ID needs to exist with at least one shopping cart operation. When Sarah added a sports shirt to her shopping cart, she was automatically placed in the segment online shoppers. This allows Luma to create and deliver personalized content at scale based on segments, for example, all customer profiles belonging to a segment can be exported and used in an email campaign. All these operations are strictly governed with privacy and preferences in mind. Numerous consumer signals are hidden in the data Luma brings together in Experience Platform. Query service and data science workspace provide tooling to uncover these hidden signals. Based on Sarah’s past visits to the Luma studio, a model in Data Science Workspace added these recommendations to Sarah’s real time customer profile. Using query service, Luma can generate insights into customer behavior and perform cross channel analysis and reporting.
Sarah’s personalized experiences were possible through the power of Adobe Experience Platform. Data Management, data governance, real time customer profiles and continuous intelligence together provide a unique advantage for Luma and a better experience for their customers. -
recommendation-more-help
9051d869-e959-46c8-8c52-f0759cee3763