Data Driven Experiences

Overview

DADI is unique in its approach to data: the entire platform is built to facilitate Data Driven Experiences.

A data driven experience is any interaction with a product (website, app or any other digital channel) that is unique to an individual as a result of decisions made on the back of person-level data.

DADI puts the concept of the individual at the heart of the platform, creating real-time, person-level taxonomies of interests, and providing multiple actionable data points to enable the construction of individual-specific experiences.

Examples of data driven experiences

A data driven experience can range from the simple to the highly complex, and can be constructed in both the anonymous and known user spaces.

One basic example is the delivery of movie reviews that respect regional embargos based on the user's location at the point of page request. Another basic example is the selection of new movie reviews that pays respect to reviews that user has already read, ensuring that they receive new content on each visit.

A more complex example would be the selection of articles for the individual based on a person-level taxonomy of interest and weighted through the use of machine learning and proximity to other users.

Another complex example is the recommendation of a new car for a user at the point that they first interact with a car reviews website, selected through the use of a proximity mapping and enhanced with machine learning as the user engages with the process. This data could then be fed through to an on-hand call centre to enable an informed and relevant concierge service to lead the user to point of delivery of their new car.

How does this work?

At the heart of the DADI platform is the concept of the anonymous UUID: a persistent anonymized user record that is available cross product. This is provided by DADI Identity.

Used in conjunction with DADI Track, Identity enables the monitoring of every action taken within a product, and can hand this data over to the known space at the point of user sign up/in.

By applying DADI Match to content, it is possible to automatically categorize content against our common taxonomical-framework (the most comprehensive framework available). Match is a machine learning layer that is capable of understanding the meaning of actions. When matched to content and tied to a UUID, this enables person-level taxonomies to be created and evolved in real time.