In this session Ron Luhtanen and Petri Mertanen will tell how Annalect Finland is using machine learning in creating predictive models, which are explaining and predicting user behavior from web analytics data. By default quite many web analytics systems report behavioral data on an aggregate level. This is inconvenient for in depth analysis, because it limits the methods to only different regression models. During the session you will hear how browser and session level data is used with modeling algorithm. We will wrap up the session with benefits and outputs of the modeling.

Matt will argue that Optimization can be, and perhaps should be, framed as a sequential decision problem. Viewing optimization this way will let us unify Testing, Targeting, and even Attribution, as interrelated subtasks. Matt will then introduce Reinforcement Learning, a method from the field of Artificial Intelligence, as a general approach to find optimal policies over multi-touch problems. Note: This talk will be mostly conceptual. I will however provide a list of resource for those interested in learning more. If you are looking for a 'three practical skills to bring back to the office on Monday' talk, you may want to skip.

The advancements in data and machine learning have resulted in some fascinating results. We will explore some exciting recent projects that are using Google Cloud and the open source library TensorFlow with the aim to inspire you to build things you may have thought were not possible.