Marek Adamove

Marek is a PhD student focusing on recommender systems, personalization, and sequential modelling. His research explores sequential patterns in user behaviour and their effective incorporation into recommendation systems with the goal of improving adaptability to individual users and their dynamic needs.

Before joining KInIT, he gained a Bachelor’s degree in Informatics and a Master’s degree in Intelligent Software Systems from the Slovak University of Technology. His passion for research began during his studies, where he developed a strong interest in machine learning and its applications to personalized systems. In his Master’s thesis, he investigated context-aware sequential music recommendation, focusing on how various types of contextual information can be incorporated into neural recommendation models.

Marek also gained one year of industry experience as a Marketing Data Scientist, where he applied various statistical and machine learning techniques to understand and optimize the impact of marketing campaigns.

Supervisor: Michal Kompan (KInIT)

The recommender systems are an integral part of almost every modern Web application. Personalized, or at least adaptive, services have become a standard that is expected by the users in almost every domain (e.g., news, chatbots, social media, or search).

The growing diversity of users, content, and contexts creates new challenges for recommender and adaptive systems. Such systems need to account for individual user preferences and behavior while also responding to changes in the users and the environments in which they operate.

The aim of this doctoral thesis is to investigate methods for developing and improving recommender systems. The research will focus on approaches that enable these systems to provide more relevant and personalized services while adapting to changing user behavior, preferences, and contexts.