TUP – Track Understand Predict

About the product

The Learning System searches systematically for the optimal ways in which institutions and retailers interact with their customers.

Environment (Stores, Classrooms, Venues):  Through the use of computer vision, radio and auditory profiling, Transport Learning tracks the changes in customers as they interact with different products across different channels.


The only requirement is the ability to consistently gather user data. This could mean access to the in-store cameras, or installing local servers.  


Environmental Parameters (Music, Colors, Store layout, Messaging, Pricing, Inventory): The content that will be displayed to the users has to be labeled as well as deployable in a modular format. Examples of these modules are lighting, playlists, store layouts, pricing, etc..


Collected user data: User data are collected, organized, analyzed, and, then, correlated with content-specific and environmental variables.  These data are the basis on which the Machine Learning Engine makes predictions of user behavior and optimizes environmental parameters. 


Machine Learning Engine: The Machine Learning Engine identifies patterns of user behavior, correlates these patterns with meaningful user outcomes (events known to positively or negatively arouse users), and predicts the optimal changes to the environment.


Accordingly, the Machine Learning Engine deploys the modules to accomplish the desired goals: higher sales, better inventory predictions, customer insights.