Inspired by the greek Greek homoios morphe (i.e. similar form) we use the term homomorphism to describe how corresponding elements of two systems behave very similarly in combination with other corresponding elements, in our case offline and online. 

“Homomorphism” represents Footprints for Retail’s advanced AI framework that empowers our unique technology to have the capability to enrich any online database, at individual user level, with their physical/offline shopping behavioral characteristics. Physical/offline behavioral data and affinity clustering is, by any means, the most valuable type of data to be used for Online Behavioral Advertising & Marketing Automation. We classify subtle physical shopping behaviors into multidimensional clusters (we use up to 48 different behavioral data dimensions) and then match these clusters with their online “twins”. This probabilistic attribution model generates unprecedented benefits for marketers and advertisers working with physical retail brands and objectives. It allows campaigns to be targeted towards very specific behavioral segments in order to Increase their Frequency of Visits, the Visit Duration, and the amount of Shops per Visit inside a certain Shopping Center, for example.

Retail Analytics technology

The section within the platform that collects the offline behaviors without which homomorphism wouldn’t be possible is called Retail Analytics. 

Built on cutting edge modern technologies and with a highly scalable architecture, Footprints Retail Analytics transforms the raw location data into accurate and meaningful insights.

Architecture type: Decentralized, based on one central hub that distributes the data, and independent nodes, one for each building (location).

Scalability: Infinite, one VM / Docker container per one location, or any number of VMs for one single but large location.

Technology:  

  • Linux-based (Ubuntu) OS
  • Node.js programming language
  • MongoDB no-sql database for data storage
  • Redis in-memory database for rapid data processing

Data Collection and Retention, GDPR

The data collected within Footprints for Retail platform is processed in three flavors, depending on the desired configuration of the system:

  1. With total MAC anonymization, meaning that each collected MAC address is fully scrambled when a visit into the building is finalized. The real MAC address is never saved into the database.
  2. With partial MAC anonymization, case when the MAC address is pseudonymized and then partially scrambled, leaving us the opportunity to still be able to track the same scrambled MAC address across visits, but assuring at the same time a high level of privacy.
  1. With no MAC anonymization, levering the full reporting power of the system, that includes various reports concerning recurrence and recency of unique or returning visitors.

 The system offers also a configurable data deletion policy (e.g. data to be automatically deleted after a period of one year).