On the case study of automated personalisation, we present how machine learning can be utilised to improve user experience by optimizing customer journey in complex environments with many parameters. In contrast to the traditional manual approach, we automate segmentation of personas as well as mapping them to relevant content.

At the core of the talk, we present a custom deep neural network which learns from customers' choices and automates the personalisation process. In addition, we are using a local pre-trained neural network to analyse images and texts, which serves as basis for matching content to users.

Finally, we build the bridge to the economic part of software development by demonstrating the integration of our personalization tool into a content management system and show how those introduced improvements create real business value by reducing the work load on editors while controllably improving conversion rates.