Hyperight

Reinforcement Learning for Email Optimization – Keenan Lyon, Leovegas Group

Premium content

Login or register to unlock the content

Session Outline

At LeoVegas, the nature of our campaigns and promotions poses interesting challenges for email optimization. The immense level of personalization available, from timing and frequency of send outs, to the kinds of promotional offers given, makes deep neural networks a necessary tool in our predictive modelling. In this session, I will be presenting how our approach allows us to determine optimal characteristics on a user-by-user basis, opening the door for emails and promotions personalised on the individual level.

Key Takeaways

– Email optimization should be done in a data-driven way, ideally using reinforcement learning

– The format of promotions in the gambling industry allow for high levels of personalization in each email

– Bayesian-based optimization methods achieve the important exploration/exploitation balance across all possible emails

Add comment