Abstract: The present disclosure provides a closed loop, self-learning system that automatically optimizes what experiences should be presented to each customer. Instead of relying on rules and external targeting, it observes customer reactions to continuously improve performance and adapt to environment changes.

Abstract: A shopping system can employ a computer-implemented method to determine whether an offer is a deal. The method comprises associating offers received for a product with the product in a database; associating a time for each of the offers noting when each particular offer was effective; receiving a current offer for the product; identifying the offers for the product in the database that are within a configured time period of the current offer; comparing the offers for the product in the database with the current offer for the product based on a set of parameters; identifying the current offer as a deal in response to a determination that the current offer satisfies all parameters compared to the offers for the product in the database. Various sets of parameters may be used to determine if the current offer is a deal with respect to previous offers.