The health crisis generated by the COVID-19 pandemic has induced, among other things, an increase in the importance of remote work or teleworking (TL) in the current period. The objective of this research is to identify the economic and social impact of telework in changing the behavior of employees in Romania. The research was conducted approximately one year after the onset of the pandemic until the beginning of the vaccination period in Romania. The research proposed includes three main directions of analysis of the extracted data, which are related to telework efficiency, this being considered one of the most important indicators for a company. In order to obtain conclusive results, we used a mixed methodology, combining results obtained through a survey based on a self-administered electronic questionnaire, with a data mining analysis. Detailed analysis of the groups identified based on work efficiency allowed us to highlight the most common employee profiles. This analysis was doubled by a second classification experiment, which provided us a more detailed analysis of the groups identified based on job satisfaction and highlighted the most common employee profiles. The expansion of telework in various economic areas is a result of adaptation to the new economic and social conditions caused by the COVID-19 pandemic.

Greenhouse gas emissions (GE) represent an element that influences the lives of all people on the planet. This action must be controlled and prevented because the negative effects are starting to appear more and more in everyday life, sometimes with devastating consequences from a climate point of view and not only for the inhabitants of certain regions. At the European level, one of the main measures taken was the implementation of the Green Deal as a response to the fight against GE. The purpose of this article is to offer a description of the main elements that are influencing the GE, as well as the role of the Green Deal. It also aims to identify the characteristics of the EU countries from the GE point of view before and after the Green Deal was proposed. In this regard two more cluster analyses are also carried out regarding GE at the European level. One analysis concerns the identification and evolution of the main groups of countries from this point of view for years 2018 and 2020. The second analysis concerns the main fields in the industry for year 2020. The used methodology was DM-CRISP. In the final part of the article the obtained results are analyzed, a discussion is added based on them and also a conclusion section.

The plan proposed within the 2030 Agenda through its specific objectives regarding sustainable development as well as through the approach to achieving a circular economy, is part of a strategy at European level for improving and preserving the environment in a sustainable manner. The recycling process as a component of the strategy has and will have a major impact on the environment. In this article, a data mining analysis is carried out regarding the recycling rate of electronic and electrical products at the European level. The analysis is carried out for two moments of time, namely the year 2018 and the year 2021. Following the clustering process of the countries from the European Union (EU), it is easier to see which countries have similar behavior from this point of view. At the same time, taking into account the two years, it is possible to observe the dynamics of the created clusters and how the European countries succeed to manage the recycling process of electronic and electrical products three years apart. The two moments were chosen taking into account the COVID-19 pandemic, the period in which, the teleworking way has occurred. For this reason, many employees had to purchase the necessary things and transform at least one room into an office. The authors’ contributions consisted in the pre-processing of data sets, the application of data mining algorithms, obtaining the results and their interpretation in the given context, commenting on the results obtained and providing answers to the research questions. The work is structured in five sections, respectively Introduction, Literature review, Methodology, Results and Discussion and Conclusion.

For the European Union, the 2030 Agenda represents a comprehensive framework that aims to achieve objectives such as sustainable development, promoting economic growth, social inclusion, and environmental protection by the year 2030. One of the main strategies of the European Union’s Agenda 2030 is to implement a circular economy (CE) with the aim of supporting elements such as sustainable development, emphasizing resource efficiency, waste reduction, and a shift towards renewable materials. One of the most important tools that can help the circular economy achieve its objectives is Machine Learning (ML). Machine Learning can transform the economy by driving innovation, improving efficiency, and enabling data-driven decision-making across industries. Circular economy and machine learning intersect by leveraging data-driven insights to optimize resource use, improve recycling processes, and enhance product life cycles for greater sustainability. The research paper’s purpose is to highlight the role that the use of ML can have in the implementation of the principles and approaches specific to the circular economy. The paper describes the specific aspects of the circular economy, types of Machine Learning algorithms and the support that ML can offer EC. A data analysis using a specific ML algorithm is also performed. However, it is important to note that the research is limited by the choice of specific methods and datasets, without extending the analysis to various economic sectors or to the political and social influences that may affect the integration of these technologies. The research also does not address the possible ethical and security challenges associated with the use of machine learning algorithms in the circular economy.

The aim of this chapter is to explore the application of data mining for analyzing academic performance in connection with the participatory behavior of the students enrolled in an online two-year Master degree program in project management. The main data sources were the operational database with the students’ records and the log files and statistics provided by the e-learning platform. One hundred eighty-one enrolled students, and more than 150 distinct characteristics/ variables per student were used. Due to the large number of variables, an exploratory data analysis through data mining was chosen, and a model-based discovery approach was designed and executed in Weka environment. The association rules, clustering, and classification were applied in order to identify the factors explaining the students’ performance and the relationship between academic performance and behavior in the virtual learning environment. Data mining has revealed interesting patterns in data. These patterns indicate that academic performance is related to the intensity of the student activities in virtual environment. If the student understands how to work and she/he is motivated to communicate with others, then he might have a good academic performance. Based on clustering analysis, different student profiles were discovered, explaining the academic performance. The results are very encouraging and suggest several future developments.