Strategic Customer Recommendations

Media / Events / Strategic Customer Recommendations
19 December. 2019, 10:00, Julia House, Ground Floor, 3 Themistokli Dervi Street, Nicosia

Strategic Customer Recommendations

Speaker: Georgios Theocharous

Strategic customer recommendations refer to the problem where an intelligent agent observes the sequential behaviors and activities of customers and decides when and how to interact with them to optimize some long-term objectives, both for the customer and the retailer. In industry, such systems do not exist and in academia they are barely beginning to find their way. In Adobe research, we have been implementing such systems for various use-cases including points of interest recommendations, tutorial recommendations and web offer recommendation for optimizing lifetime value. There are many research challenges when building these systems, such as modeling the sequential behavior of users, deciding when to intervene and offer recommendations without annoying the user, multi-objective optimization of the user experience and the retailer value, building systems from passive data that do not contain past recommendations, scaling to large action spaces, handling non-stationarity and incorporating human cognitive biases. In this talk I will cover various use-cases and research challenges we solved to make these systems practical.


Georgios received his Ph.D. degree in computer science in 2002 from Michigan State University. From 2002 to 2004, he was a post-doctoral associate at the Computer Science and Artificial Intelligence Lab at M.I.T. In October 2004, he joined Intel Research as a research scientist and in July 2011, he joined Yahoo! Labs as a scientist. Finally, he joined Adobe Research as a senior research Scientist in July 2012. Georgios’ interests include scaling up computational models of learning and planning under uncertainty and their applications to the real world. His projects have evolved over time from building intelligent agents that interact with the world, such as robot navigation, to agents that interact one to one with people, such as a personal and physical math coin tutoring system, to large scale interactions, such as marketing and advertising agents that interact with millions of people. These interaction systems reason over the evolution of people’s behaviors and guide them to achieve long-term goals.

Subscribe to our Newsletter

* indicates required