Visit objectives: 

• Gather empirical data and conduct research focused on investigating the green bond markets’ volatility spillovers, by using green bond index yield rates’ data. For this purpose, several WUT electronic resources were accessed and Nevena had multiple discussions with ECREB members;  
• Explore collaboration opportunities (joint preparation of papers, project proposals), showcase the IES’ resources to the ECREB representatives, engage in discussions, and attend the ECREB Research e-Seminar;
• Seek counselling and mentorship from ECREB researchers on scientific matters. 

Summary: During the last decades, the prediction of the unemployment rate started to be a favourite subject of investigation for many researchers. Over time, the topic gradually grew in importance, especially with the development of modern digital computational technology.

The aim of this research is to predict the unemployment rate based on a set of input parameters, including Artificial Intelligence (AI). The forecasting follows the Artificial Neural Networks (ANNs) methodology by considering a sample of 23 high-tech and developed countries, over the 1998-2016 years. The theoretical framework is given by the discussion related to the “Philips’ curve” (Phillips, 1958) and the “Okun’s law” (Okun, 1962) as they are modelled by Dornbusch et al. (2017) and Folawewo and Adeboje (2017), but controlling for AI (Mutascu, 2020).

The contribution of the research is threefold. First, to the best of our knowledge, this is a pioneer work in unemployment forecasting, which uses AI as a core determinant. Second, the research is one of the first contributions considering ANNs for the prediction of unemployment by using AI as an input parameter. Unlike the classical time-series methods, ANNs have the ability to learn and model non-linear processes, they can be generalized by predicting unseen data, and do not impose any restrictions or special statistical treatments on the input variables. Third, compared with the existing literature, the study offers an extended dataset by including many countries over a large period of time.

Summary: Fuel prices represent one of the main cost elements for all goods and services. They are largely in-fluenced not only by international oil prices, but also by fuel tax systems, cost prices, and profit margins of oil companies. Therefore, understanding how fuel prices co-move has multiple eco-nomic implications. First, gasoline and diesel prices have different effects on transportation costs. If households mainly use gasoline engines, diesel engines dominate the industrial transportation sector. Second, given the different impact that gasoline and diesel combustion has on the envi-ronment, governments might apply different excise and value-added taxes on these two categories of fuels.

The aim of this research is to investigate the co-movements of gasoline and diesel prices in three European countries (Germany, France, and Italy), with different fuel tax systems in place. The methodology follows a Machine Learning (ML) approach (Magazzino and Mele, 2021) to es-timate the presence of co-movements and a hypothetical latent factor in our weekly data, spanning the period from January 2005 to June 2021.

To the best of our knowledge, this is the first research that uses Artificial Intelligence (AI) tools to explain the co-movements of gasoline and diesel, showing a latent factor.

Bio: Ginevra Gravili graduated in Economic Studies in 1992 and she achieved PhD in Management and Organization in 1996. Since 2002, she is professor of Organization Theory at University of Salento, Department of Economics, Lecce, Italy. She has written numerous books with national and international editors and articles. Her research areas examine: sme’s, knowledge sharing, social recruitment, HRM of public administration, ICT, social media communication, supply chain management and sustainability in HRM.

Bio: Marco Benvenuto graduated in Economics and Business at the University of Salento. He had undertaken a specialization path in Economics and Management in Health, starting from the training offered by the ESTRIS Master (Expert of Innovation Transfer in Health) that ISBEM organize as result of a MIUR research announcement. After the Master he won a PhD at University of Pisa on the subject of “Technology for Health: evaluation of management innovations in the biomedical field”, at the University of Pisa. My academic work in this field of research led me to collaborate with prestigious Universities and Schools of High-level Specialization including the University of Pisa, Scuola Superiore Sant’Anna, the Universities of Oslo and Antwerp, the University of Foggia, Tor Vergata, the University of Salento, Nostra Signora del Buon consiglio Università of Tirana and LUM Jean Monet.
    Since 2015, he is researcher and aggregate professor of Management of Public Administration at University of Salento, Economics Department. He has written numerous scientific articles with national and international editors. His research area examine: accounting, management in health care and  risk management.