The importance of data and evidence has increased considerably in policy planning, implementation, and evaluation. There is unprecedented availability of open and big data, and there are rapid developments in intelligence gathering and the application of analytical tools. While cultural heritage holds many tangible and intangible values for local communities and society in general, there is a knowledge gap regarding suitable methods and data sources to measure the impacts and develop data-driven policies of cultural tourism. In the tourism sector, rapid developments are particularly taking place around novel uses of mobile positioning data, web scraping, and open application programming interface (API) data, data on sharing, and collaborative economy and passenger data. Based on feedback from 15 European cultural tourism regions, recommendations are developed regarding the use of innovative tools and data sources in tourism management. In terms of potential analytical depth, it is especially advisable to explore the use of mobile positioning data. Yet, there are considerable barriers, especially in terms of privacy protection and ethics, in using such data. User-generated big data from social media, web searches, and website visits constitute another promising data source as it is often publicly available in real time and has low usage barriers. Due to the emergence of new platform-based business models in the travel and tourism sector, special attention should be paid to improving access and usage of data on sharing and collaborative economy.

This paper aims to assess the economic development and development policies in the Central and Eastern European (CEE) countries in 1990–2005, from the collapse of the USSR to the enlargement of the European Union. A great number of authors have generally seen the transition as a very positive process. They have concluded that the reform policies focusing on macroeconomic and price stability have been the key to success for CEE economies. A reliable economic environment is, of course, instrumental for longer-term economic success, as exemplified by the prolonged crisis in most of the former Soviet Union. Our analysis of the economic development and competitive advantages in the region, however, leads to the conclusion that the specific approach to transition that the Central and Eastern European countries followed came at a rather high cost. Comparative neglect and weakness of a set of policies crucial for longer-term development, such as science, technology and innovation policies, has led to deterioration in the last decade rather than the strengthening of the competitive advantages of Central and Eastern European economies. Furthermore, we argue that, in most cases, CEE countries have unfortunately overlooked or misjudged a number of development challenges, and have thus implemented policies that have generated growth at the cost of rapidly increasing risks. This is how the financial fragility of several Central and Eastern European countries has recently increased drastically, and the region seems to have virtually arrived at the brink of economic collapse. Since the CEE countries joined the European Union, the CEE governments have gradually moved towards acquiring a more active role in economic development. These policies need, however, to be strengthened considerably and reinforced by macroeconomic policies that curb current excessive dependence on foreign-financed growth.

In the realm of international trade and economic development, the prediction of trade flows between countries is crucial for identifying export opportunities. Commonly used log-linear regression models are constrained due to difficulties when dealing with extensive, high-cardinality datasets, and the utilization of machine learning techniques in predictions offers new possibilities. We examine the predictive power of Graph Neural Networks (GNNs) in estimating the value of bilateral trade between countries. We work with detailed UN Comtrade data that represent annual bilateral trade in goods between any two countries in the world and more than 5000 product groups. We explore two different types of GNNs, namely Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs), by applying them to trade flow data. This study evaluates the effectiveness of GNNs relative to traditional machine learning techniques such as random forest and examines the possible effects of data drift on their performance. Our findings reveal the superior predictive capability of GNNs, suggesting their effectiveness in modeling complex trade relationships. The research presented in this work offers a data-driven foundation for decision-making and is relevant for business strategies and policymaking as it helps in identifying markets, products, and sectors with significant development potential.