Recommendation models for dynamic spatiotemporal big data

Recent years, the evolving nature of social networks has led to the expeditious growth of the internet and the rapid increment of the data on a global scale. The need of accessing and retrieving relevant information close to users’ preferences is an open problem which continuously raises new challenges for recommender systems. To over come this problem many researchers focused on creating models that provide personalized recommendation in order to assist users making choices. In this context, a new research area in information systems has emerged over the last decades to respond to these challenges. This research area is called recommendation systems and focuses onmodelling and analyzing data in order to retrieve relevant information based on users’ preferences and to suggest some new alternatives. More specifically, information related to user interactions on a social network is used to associate them with other users, new locations, or products with which they have not interacted yet. There are four main approaches in literature which distinguish the recommendations systems into: 1) content-based, 2) collaborative filtering, 3) knowledge-based, and 4) hybrid (Hybrid). Each of these approaches has significant advantages, as well as drawbacks, which have led research to the adoption of hybrid systems that combine some of the above-mentioned techniques in order to personalize the recommendations and to fill the shortcomings, each technique has separately. The exploitation of information in large amounts with the existingmodels is not sufficient since power law distribution of the data causes sparsity problem and makes personalization a difficult task. More specifically, models predictions accuracy is higher for users with large past history than for userswith a few interactions. This problem is also known as “Cold Start” according to which it is attempted to retrieve relevant information based on small past history and to associate these users with other users, locations or products. In this problem, we should also examine the dynamics of users’ preferences among time periods, which continuously alternate the precision of prediction models. This evolution of their preferencesmaybe due to: 1)New items exploration: curiosity leads users to explore new items contrary to their ordinary choices, 2) User experience: if a user had a pleasant