Abstract
Abstract This paper aims to identify changes in consumption by students from Albania, Poland and Portugal in the era of the SARS-CoV-2 coronavirus. The study was conducted on a sample of 668 students of the Qiriazi University College and Aldent University in Albania, the University of Warmia and Mazury in Olsztyn, Poland and the School of Technology and Management of Porto Polytechnic in Portugal. The estimated volumes of basic macroeconomic indicators for this period prove that the crisis caused by the COVID-19 epidemic may be the cause of many adverse changes in various areas of life. The empirical study aimed to determine the impact of the epidemiological situation on changes in the shopping habits of students – designated as young consumers. The main goal was to identify differences in the purchasing decisions of young consumers depending on gender and nationality. The research instrument was a standardized survey questionnaire, which was divided into three thematic blocks. The first part of the questionnaire contains questions on the housing conditions of students, in the second part – activity on the labor market, and in the third part – issues related to shopping and the use of cultural services and the way of spending free time. Some conclusions were drawn from the research: (1) pandemic did not change the periodicity of purchases, (2) from online buying did not show a boom in the samples analyzed in this study, (3) students from these countries changed their shopping behavior in terms of shopping places. The conclusions formulated in the study, as well as the topicality of the issues, allow them to be considered useful for institutional entities interested in observing changes in consumption during the pandemic. The scientific contribution of theoretical and empirical considerations is primarily the systematization of theoretical foundations and the conceptualization of the category of factors determining the diversity of purchasing behavior of young people (students).

Abstract
Gamification is a topic which aims to apply game elements to real world tasks, that results in a pleasant influence over a user behaviour towards an objective. Learning is one of the fields where gamification has been implemented and experimented to motivate students and improve their learning process. The first iterations account for the use of game elements such as points, levels and badges or achievements based on task completion according to rules set before. The learning tasks in this approach are not necessarily changed or take advantage of new forms of interactions and guidance. In this article we introduce the application of virtual reality, augmented reality, and machine learning as tools to improve upon the standard application of gamification, making the experience more immersive to the user. We hope to advance gamification to account for more elements, such as digital twins and digital aids in a learning application. In this article we detail possible scenarios for the application of virtual reality and augmented reality combined with machine learning in serious games and learning scenarios.

Abstract
Machine Learning has been evolving rapidly over the past years, with new algorithms and approaches being devised to solve the challenges that the new properties of data pose. Specifically, algorithms must now learn continuously and in real time, from very large and possibly distributed sets of data. In this paper we describe a learning system that tackles some of these novel challenges. It learns and adapts in realtime by continuously incorporating user feedback, in a fully autonomous way. Moreover, it allows for users to manage features (e.g. add, edit, remove), reflecting these changes on-the-fly in the Machine Learning pipeline. The paper describes some of the main functionalities of the system, which despite being of general-purpose, is being developed in the context of a project in the domain of financial fraud detection.

Abstract
Artificial Intelligence is a hot topic and Machine Learning is one of the most fluent approaches and practices. The problem with many AI models is that they can be useful for predicting but they are bad at explaining why they behave a certain way. In some contexts, the explanation may even be more important than the prediction itself, mainly in systems in which decisions are made based on their predictions. Therefore, it is increasingly necessary to provide a forecast accompanied by an explanation, when decisions are made automatically. This paper aims to contribute to the solution of problem based on human mobility research, or at least, to be a starting point for its solution.

Abstract
In a time in which streaming data becomes the new normal in Machine Learning problems, to the detriment of batch data, new challenges arise. In the past, a data source would be static in the sense that all data were known at the moment of the training of the model. A model would be trained and it would be in use for relatively long periods of time. Nowadays, data arrive in real-time and their statistical properties may also change over time, rendering trained models outdated. In this paper we propose an approach to deal with the concept drift problem with minimal computational effort. Specifically, we continuously update an ensemble with new weak learners and adjust their weights according to their performance. This approach is suitable to be used in real-time in the form of an ever-evolving model that adapts to change in the data.

Abstract
Machine Learning has emerged in the last years as the main solution to many of nowadays' data-based decision problems. However, while new and more powerful algorithms and the increasing availability of computational resources contributed to a widespread use of Machine Learning, significant challenges still remain. Two of the most significant nowadays are the need to explain a model's predictions, and the significant costs of training and re-training models, especially with large datasets or in streaming scenarios. In this paper we address both issues by proposing an approach we deem predictive and user-centric. It is predictive in the sense that it estimates the benefit of re-training a model with new data, and it is user centric in the sense that it implements an explainable interface that produces interpretable explanations that accompany predictions. The former allows to reduce necessary resources (e.g. time, costs) spent on re-training models when no improvements are expected, while the latter allows for human users to have additional information to support decision-making. We validate the proposed approach with a group of public datasets and present a real application scenario.