The 22nd International Conference on INFORMATICS in ECONOMY

(IE 2023)

Education, Research & Business Technologies

Bucharest, Romania, May 25-26, 2023


Big Data Management, Processing and Analytics, IT Deployment in Cultural Institutions & Smart Cities and Sustainable Communities


Liat TODERIS, Ariel University, Israel

Iris REYCHAV, Ariel University, Israel

Roger McHANEY, Kansas State University, KS USA

Abstract: Healthcare systems produce big data with latent capabilities for healthcare providers. Big data is a strategic resource and requires the appropriate infrastructure for data entry, systematic analysis, and visualizations for decision makers. Attempts to build a big data infrastructure raise various challenges related to availability, accessibility, reliability, and quality, while considering information privacy and security. These challenges are significant and can disrupt the ability to realize data’s hidden potential. A variety of technological tools are available to medical staff members for big data use in healthcare. However, access to the data alone does not guarantee the appropriate use of these tools and still requires understanding needs of end users to ensure success. In recent decades, several models have been developed to evaluate the implementation of new information technology and the adoption of technology by users. The current paper focuses on this value and related challenges: how to turn organizational data into meaningful knowledge, by introducing a new implementation model in big data in healthcare. The model is an integrated one, presenting practical aspects, timeline aspects related to the life of the project, personalization in access to data, reference to information providers, and technological solutions. The project uses an organizational architecture tool to describe the implementation model and generate outcomes. The model will be based on 15 clinical and managerial use cases. Outcomes will be described by strategic objectives in the model and will be presented in the ArchiMate® language.

Keywords: Healthcare, Big Data, Organizational Architecture



Jan W. Owsiński, Systems Research Institute, Polish Academy of Sciences, Poland

Marek GAJEWSKI, Systems Research Institute, Polish Academy of Sciences, Poland

Abstract: There are problems in data analysis, in which we should distinguish between two fundamentally different categories (false-true, for-against, bad-good,…), but in which we do not know the actual structure of the data set considered, and there is no appropriate knowledge of the ground truth to potentially categorize or distinguish the observations. In this particular paper we are concerned with the data on ad-related web traffic, in which we would like to tell the genuine human-generated traffic from the artificial bot-generated one. Yet, this dichotomy, even if of primary importance from the point of view of the respective “business model”, turns out to be far too simplistic when confronted with the results of analysis. We show how in the study process the awareness appears of a multiplicity of behavior patterns in the traffic analyzed, contributing also to the achievement of improved results. It is shown how quite simple clustering tools may provide effective identification of such patterns and their characteristics. A cognitive value added is also constituted by the very categorization of the behavior patterns identified and their relative persistence. The lessons learned may be of use for various analyses of similar nature, where apparently simpler divisions, assumed at the outset, can only be effectively analyzed when perceived in their fuller complexity. It is also possible, given the deeper justification of the results obtained, that the concrete categorizations identified are of a wider significance than just for the case considered.

Keywords: Behavior patterns, clustering, web advertising, bots, humans



Dragoș-Cătălin BARBU, Bucharest University of Economic Studies, Doctoral School of Economics Informatics

Adela Bâra, Bucharest University of Economic Studies

Simona-Vasilica OPREA, Bucharest University of Economic Studies

Abstract. This paper explores the impact of Electronic Cash Registers (ECRs) on tax collection and aims to provide an overview of the implementation of Electronic Fiscal Devices (EFDs) in Romania, describing the legal framework, the challenges faced during implementation, and the benefits and drawbacks of this system. Benefitting from a thorough literature review and analysis of empirical studies, we present findings on the effectiveness of ECRs as a tool for tax control and revenue enhancement, as well as the factors influencing their adoption and success. Our results suggest that ECRs have a positive impact on tax compliance and revenue collection in many countries, although their effectiveness may depend on factors such as government support, technology infrastructure, and local tax culture. We also identify areas for further research on the use of ECRs, including the potential for blockchain-based ECRs and the role of artificial intelligence in tax collection. Overall, this article contributes to the ongoing discussion of how technology can be used to improve tax collection and reduce tax evasion worldwide.

Keywords: Electronic Cash Registers, Electronic Fiscal Devices, tax collection, Big Data, data analysis



Diana Andreea CAUNIAC, Bucharest University of Economic Studies

Mihaela Andreea NICULAE, Bucharest University of Economic Studies

Abstract: Monitoring the performance of a database is the act of measuring the performance of a real-time database in order to determine problems and other factors that can cause problems in the future. It is also a good way to deter-mine which areas of the database can be improved or optimized in order to increase efficiency and performance. This is usually done by software and monitoring tools, either incorporated into the database management software or installed from third-party suppliers. The main objective of database performance monitoring is to evaluate the performance of a database server, for both hardware and software. This involves taking snapshots of performance over time to determine the exact moment that problems such as crashes occur, so you can understand exactly what caused those problems at that exact time and hopefully find a proper solution. Through this paper, you will find a short introduction regarding the true meaning of database performance and the aspects that need the most attention when making an analysis. You will also find a comparison between the performance of two databases and what could be improved.

Keywords: Big Data Management, Processing and Analytics



Anda BELCIU, Bucharest University of Economic Studies

Alexandra CORBEA, Bucharest University of Economic Studies

Vlad DIACONITA, Bucharest University of Economic Studies

Iuliana SIMONCA, Bucharest University of Economic Studies

Abstract: The article presents a study that explores the relationship between income inequality and education-related factors in various countries, through the use of PISA test results as well as the Gini coefficient and k-means clustering algorithm as tools for analysis. The Program for International Student Assessment (PISA) test results represent an important and relevant tool to measure education quality throughout the globe, as the test is taken in more than 80 countries, while the Gini coefficient measures the degree of economic inequality within a population. The paper first describes the data and methods used, including the extraction, cleaning, and merging of data from multiple sources using Python libraries. K-means clustering and Spectral Clustering were then applied to the data to cluster the countries based on their Gini coefficient and PISA results for Science, Reading, and Math in 2012, 2015, and 2018. Overall, the study seeks to offer a comprehensive analysis of the relationship between income inequality and education worldwide.

Keywords: PISA, Gini coefficient, k-means algorithm


6. Leveraging Website Analytics to Enhance User Experience with Pop-ups and Drive Sales Conversions

Marian Pompiliu CRISTESCU, Lucian Blaga University of Sibiu

Dumitru Alexandru MARA, Lucian Blaga University of Sibiu

Raluca Andreea NERIȘANU, Lucian Blaga University of Sibiu

Lia Cornelia CULDA, Lucian Blaga University of Sibiu

Abstract: This paper explores the potential of leveraging website analytics to optimize the display time of pop-up notifications using custom scripts developed with PHP, JavaScript, and MySQL. By analyzing user clicks and scrolls, an optimal inactive threshold for displaying pop-ups is determined to encourage users to take-action during their shopping sessions. The methodology demonstrates the capability of utilizing website analytics to improve UX and engagement, with the custom scripts showcasing the flexibility of combining PHP, JavaScript, and MySQL for capturing and analyzing user interaction da-ta. However, the study acknowledges limitations, including the actual impact on user engagement, conversion rates, and sales, which needs to be quantified through robust evaluation processes such as A/B testing or user testing. Despite its limitations, the study serves as a valuable starting point for future research in web analytics and UX optimization. Thus, this paper contributes to the growing body of knowledge on utilizing website analytics to improve user experience and engagement in e-commerce. By refining and extending the proposed methodology, researchers and practitioners can develop more effective strategies for tailoring website content and notifications, leading to higher user satisfaction, engagement, and conversion rates in the e-commerce domain.

Keywords: Website Analytics, E-commerce, user experience


7. The Intersection of Circular Economy, Maker Culture, and Artificial Intelligence: A Promising Path to Sustainability

George SUCIU, Beia Consult International

Mari-Anais SACHIAN, Beia Consult International

Sorina MITROI, Beia Consult International

Cosmina STALIDI, Beia Consult International

Abstract: As the impact of landfills and waste incineration on the environment be-comes more apparent, recycling has become a pressing issue. The importance of sustainability in the face of environmental concerns has led to increased interest in the circular economy, which focuses on reducing waste and maximizing the lifespan of materials by keeping them in use for as long as possible. At the same time, maker culture has grown in popularity, emphasizing creativity, DIY values, and the use of technology. This article explores the relationship between these two concepts and their potential to promote sustainable practices in product design, manufacturing, and consumption. Additionally, the article introduces the RRREMAKER project, an initiative that aims to address the issue of waste management by connecting recyclable material collectors with eco-friendly designers and producers using artificial intelligence-based technology. To address the issues with green and circular economies, machine learning, data management, and cloud environments, this interdisciplinary project brings professionals in design, materials, manufacturing, supply management, economy, distribution, and computational areas. The RRREMAKER initiative could significantly improve the world’s socioeconomic and environmental problems.

Keywords: Circular Economy, Artificial Intelligence, Sustainability


8. An analytical framework for pervasive games in the cultural sector: expanding the boundaries of play in 8 dimensions

Diane DUFORT, Université Catholique de l’Ouest

Abstract: Pervasive games have the particularity of using Information Technologies to blur the boundaries between a game experience and the “ordinary” world, thus blending the game world in the player’s everyday life. In the cultural sector, they have been used to promote cultural practices, events and to provide enhanced visits. Pervasive Games are complex objects and their production requires the work of an interdisciplinary team (e.g. game designers, developers, artists, instructional designers, experts) composed of specialists and non-specialists of games. Our aim is to build methodological tools, such as a design framework, to help team members a) describe and analyse pervasive games while considering the wide variety and heterogeneity of media productions used in that particular type of games; and b) explore the specificities of pervasive games in terms of narration, structure and usage of IT to blur the boundaries between the game world and the “ordinary” world. To build our framework, we analysed 47 pervasive games in the cultural sector. We identified dimensions that convey extensions of the boundaries of pervasive games beyond the three elementary dimensions (social, spatial, temporal). We discuss further perspectives of this work, such as the ex-tension of the framework and its evaluation.

Keywords: Pervasive games, cultural heritage, design framework


9. The Costs of Virtual Solutions for the Educational System

Lorena BĂTĂGAN, Bucharest University of Economic Studies

Cristian CIUREA, Bucharest University of Economic Studies

Abstract: The last years, during the pandemic context, made us think that it is very important to have virtual solutions to sustain the educational process. Virtual solutions like Virtual Reading Rooms (VRRs), Virtual Teaching Spaces (VTSs), and Virtual Exhibitions (VEs) represent real support for sending information and interconnecting the students with teachers, and delivering knowledge in an efficient way. Starting from this point of view, we identified the costs of virtual solutions in this case and we highlighted the benefits of this type of applications.

Keywords: Virtual solutions, virtual reading rooms, virtual teaching spaces, education, costs


10. Educational innovations based on metaverse in the development of smart cities

Alin ZAMFIROIU, Bucharest University of Economic Studies, National Institute for Research & Development in Informatics, Bucharest, Romania

Ramesh C SHARMA, Dr B R Ambedkar University Delhi, New Delhi, India

Ella Magdalena CIUPERCĂ, National Institute for Research & Development in Informatics, Bucharest, Romania

Abstract: The metaverse, a virtual world that is a highly immersive and interactive environment, can help in developing smart cities in several ways. It can be used as a platform for collaborative learning and experimentation with new urban planning strategies. This can help policymakers and stake-holders to simulate different scenarios and test the effectiveness of smart city technologies in a virtual environment before implementing them in the real world. The learners gain practical knowledge of smart city concepts such as IoT, AI, and sustainability, enabling them to develop the skills needed to participate in the development and maintenance of smart cities. The metaverse can also promote citizen engagement and participation in the development of smart cities. By providing a platform for virtual town halls, public meetings, and feedback mechanisms, the metaverse can enable citizens to participate in the planning and decision-making processes that shape the future of their cities. Smart cities are becoming a reality with the integration of technology in urban planning and development. The metaverse, a virtual world, is a promising platform for creating immersive educational experiences. In this paper, we explore the potential of metaverse-based educational innovations in the development of smart cities. Metaverse-based educational experiences can provide learners with practical knowledge of smart city concepts such as IoT, AI, and sustainability in a virtual environment. The use of virtual worlds can also allow for collaborative learning, which is crucial for the development of smart cities. The metaverse can also serve as a testbed for smart city technologies, al-lowing policymakers and stakeholders to experiment with different urban planning strategies

Keywords: Smart cities, metaverse, education, collaborative learning, citizen engagement



George SUCIU, Beia Consult International

Lucian-Alexandru NECULA, Beia Consult International

Cosmina Stalidi, Beia Consult International

Madalin SILION, Beia Consult International

Abstract: The concept of Fintech has made significant strides into the banking and finance industry all over the globe, boosting integration, utilization and recognition. The financial industry is being dominated by digital financial services. The expansion of digitalization, financial technology, the Fourth Industrial Revolution as well as the pandemic have all contributed to this. The deployment of financial technology and 4th industrial revolution technology in the financial sector has not been constrained to underdeveloped countries. 4IR instruments including such Artificial Intelligence, Big Data, the Internet of Things, Cloud computing, and Blockchain technologies have been utilized to enhance finance industry service delivery and widen financial technology inclusion. The paper is based on the European FINSESCO project, which aims to empower a rising tide of emission reduction initiatives besides facilitating the institution of Energy Performance and Energy Savings Performance Contracting EPCo/ESPCo through middle digitalization of power generation procurement (and the recruitment process for public institutions and multinational organizations).

Keywords: Fintech platform, energy saving contracting, renewable energy contracting


12. Blended Learning Implementations – A Key For Integrating Romania In Education 4.0

Andreea-Cristina STROE, Bucharest University of Economic Studies

Abstract: Education 4.0 is the new educational age, arisen as a result of Industry 4.0, where technology has gained control over all spheres of our life. Education could not have been an exception, so an expression of the digital area in the field of education is undoubtedly the blended learning model. In recent years, it has been adopted in many education systems throughout the world. Romania has still a timid approach regarding the integration of blended learning in the undergraduate system. Thus, this paper has the goal to provide a practical implementation of a possible blended learning model that could be integrated in K-12 education in Romania. Firstly, this study will briefly do an analysis of the solutions that the Ministry of Education has already tested. Secondly, the paper will attempt to create a blended learning model suitable for the undergraduate education system, with the focus on the field of learning foreign languages. Finally, the advantages and challenges of a such implementation will be discussed. Overall, the contribution of this paper to the literature consists in revealing a prototype of blended learning model that can be tested in the educational environment of Romania. Moreover, it offers visibility to the subject of blended learning in the context of K-12 education.

Keywords: Blended learning, Romanian Undergraduate Education System,

Digitalization, blended learning models


Digital Business and e-Transformation

1. The Use of Blockchain Technology for Managing a Voting Process

Oana-Alexandra DRAGOMIRESCU, Bucharest University of Economic Studies

Andreea-Izabela BOSTAN, Bucharest University of Economic Studies

Abstract: In recent years, we’ve witnessed remarkable advancements in technology, yet the world of blockchain remains enigmatic. At its core, a blockchain is an open, distributed ledger – a series of interconnected blocks containing information. One of its most intriguing features is that once data is recorded within a blockchain, altering it becomes incredibly challenging. Inspired by this concept, the authors developed a voting application that allows administrators to create voting sessions for a limited period. By employing it, we can reduce the costs associated with organizing a voting session, observe responses in real-time, and eliminate human errors in vote counting. Furthermore, it enables voting to occur anytime and anywhere if an internet connection is available. Harnessing the power of blockchain, we can transform the voting process into a more secure, transparent, unalterable, and reliable experience.

Keywords: blockchain, voting application, e-voting, smart contracts


2. Exploring the relationship between AI adoption and the integration of digital technology in enterprise

Ioana Andreea Bogoslov, Lucian Blaga University of Sibiu

Eduard Alexandru STOICA, Lucian Blaga University of Sibiu

Dorin BAYRAKTAR, Lucian Blaga University of Sibiu

Abstract: In recent decades, digital technologies undeniably have become integral parts of our everyday lives, and businesses cannot afford to ignore them. Digital technologies have revolutionized the way companies operate and communicate with their customers. Thus, adopting digital technologies in businesses has become an essential aspect of their growth and development. It has also become critical for businesses to embrace digital technologies to remain competitive and meet customer expectations. As enterprises increasingly adopt digital technologies, there is growing interest in the relationship between this trend and the adoption of artificial intelligence (AI). With the growing prevalence of digital technology in businesses, AI has become a crucial tool for improving efficiency, productivity, and decision-making, inter alia. The current research aims to examine the relationship between the level of enterprises that use at least one of the AI technologies and the Integration of Digital Technology dimension from the DESI Index, measured by its sub-dimensions. The results show a positive correlation between the level of AI technology adoption by enterprises and their digital performance. Stated differently, countries registering more widespread AI adoption tend to achieve higher levels of digital integration at the business level. Indirectly, the current analysis findings suggest that policymakers and business leaders should focus on creating a supportive environment for digital innovation to foster the growth of AI and other emerging technologies. The results could also have implications for researchers interested in understanding the role of AI and digital technology in driving economic growth and competitiveness in the digital era.

Keywords: Artificial Intelligence, Business, Enterprise, DESI Index



Stefka PETROVA, University of Economics – Varna

Pavel PETROV, University of Economics – Varna

Abstract: Determining the level of digitalization in existing digital business processes that are subject to development, as well as in the creation of new digital business processes or solutions, is an important stage in the digitalization process. In this re-search a few digital maturity models are presented – the “Digital Maturity Model” of Deloitte, the “Open Data Maturity Model” of the “Open Data Institute” and the “Open Digital Maturity Model” of the organization “Open ROADS”. They are suitable as a starting point for determining the degree of digitalization required. On this basis, guidelines in digitalization of a new business solution are pro-posed. It is possible to define and use a specialized system of indicators suitable for all business organizations operating in a certain branch of the economy. The purpose of this system of indicators is to measure the level of digitalization for the development of existing digital business processes, as well as for the creation of new digital business processes, with a view to building a new business solution.

Keywords: Digitalization, Open Data Maturity Model, Open ROADS Model


4. Analyzing the antecedents of fake news sharing in online social network

Luigia-Gabriela STERIE, Babeş-Bolyai University

Dan-Andrei SITAR-TĂUT, Babeş-Bolyai University

Daniel MICAN, Babeş-Bolyai University

Abstract: The rapid development of artificial intelligence and the increase in the number of fake news spread on online social networks pose a global problem with harmful consequences. This study aimed to analyze the influence of various variables on the distribution of fake news on social media. The study comprised 275 participants and we analyzed the data using Partial Least Squares – Structural Equation Modeling (PLS-SEM). The study found that factors such as pass time, information sharing, social media fatigue, and self-disclosure play an important role in the distribution of fake news among users. However, altruism, socialization, information seeking, and online trust do not influence the distribution of fake news. The results have important implications for researchers, social media users, businesses, organizations, and governments, as fake news can affect any domain. Therefore, it is recommended to develop algorithms and technologies used by social media platforms to detect and remove false content, and to create educational programs to teach users to identify and report fake news.

Keywords: Fake news sharing, user behavior, online social networks, behavioral intention


5. Artificial intelligence: Friend or foe? Experts’ concerns on European AI Act

Anamaria NASTASA, National Scientific Research Institute for Labour and Social Protection   

Monica Mihaela MAER MATEI, National Scientific Research Institute for Labour and Social Protection

Cristina MOCANU, National Scientific Research Institute for Labour and Social Protection

Abstract: In the last decade, there have been numerous innovations in artificial intelligence technologies in many domains, many innovations more or less favorable. However, artificial intelligence was and is the subject of multiple controversies, such as the perpetuation of inequalities, discrimination, biased decisions, and other issues regarding transparency and data protection. These problems destroy the trust of citizens and institutions in artificial intelligence. Consequently, European Commission proposed the AI Act, a regulation for assessing Ai products or services. Our study explores experts’ main concerns on artificial intelligence technologies. In the present paper, we analyzed the feedback provided by 262 stakeholders on the proposal of the European Commission regarding artificial intelligence through a text mining approach using Latent Dirichlet allocation. The LDA model produced 12 topics. The topics with the higher probability were related to AI applications in industry, transparency and responsibility, and AI technologies testing. The analysis also revealed topic differences based on the type of organization, especially consumer organizations and academic/research institutions.

Keywords: Artificial Intelligence, AI Act, Text Mining, Latent Dirichlet allocation


6. Considerations about the regulatory framework of cryptocurrency

Crina Anina BEJAN, “Aurel Vlaicu” University of Arad

Mihaela MUNTEAN, West University of Timisoara

Domninc BUCERZAN, “Aurel Vlaicu” University of Arad

Camelia Daciana STOIAN, “Aurel Vlaicu” University of Arad

Abstract: Since their development, cryptocurrencies have influenced the economic, government and financial world both with positive and negative effects. Cryptocurrency ecosystem and its ongoing development is considered to be an alternative to the traditional centralized payment system monopolized by banking institutions. Using blockchain technology, cryptocurrency offers a decentralized and secured environment for payments without a central institution to guarantee the transactions. Because this subject is still in its beginnings the regulatory systems around the world haven’t yet developed any unanimously recognized regulations. In this paper we propose a research regarding the regulatory standings of cryptocurrency around the world. Also, we identify the positive directions of further development of this subject as well as the elements with a negative impact that is recommended to be avoided.

Keywords:  Cryptocurrency, crypto regulation, blockchain



Margarita BOGDANOVA, Tsenov Academy of Economics, Svishtov

Evelina PARASHKEVOVA-VELIKOVA, Tsenov Academy of Economics, Svishtov

Abstract. The purpose of the research is to present the results of a survey of the attitudes of students in economics, administration, and management at the “D. A. Tsenov” Academy of Economics and to discuss possible approaches for managing the digital transformation of education in the context of the general framework for a digital future of society. Data from an empirical study conducted for two consecutive years among students using an e-survey (N2021=105, N2022=118) were used. The results show an improvement in students’ attitudes towards remote forms of synchronous and asynchronous learning, but also a need to invest both in hard measures – new communication channels, applications, and technical solutions, as well as in pedagogical skills for working in a hybrid environment.

Keywords: Digital transformation in education, management of digital transformation, student attitudes


8. Regional development and the role of public sector digital maturity

Mariela STOYANOVA, Tsenov Academy of Economics

Asen BOZHIKOV, Tsenov Academy of Economics

Iskren TAIROV, Tsenov Academy of Economics

Abstract: The aim of the publication is to establish the digital maturity of public structures in Bulgaria based on empirical research and the use of a model, adapted for public administration. The obtained results were used to detect logical connections and study the impact of digital maturity on economic regional development. In this regard, two planning regions with the highest relative share of survey’s response rate are further analyzed and compared. Key results were formulated through the methodology used, which included expert assessment, GAP analysis, comparative analysis and a survey with a view to self-assessment according to specified criteria. In this regard, the conceptual framework of the study outlined an indirect relation between the degree of digital maturity of the analyzed regions and their economic development, consisting mainly in stimulating the investment ecosystem in the respective territory.

Keywords: Digital maturity, digital transformation, regional development, public sector, administrative e-services


9. Enhancing the Financial Sector with Quantum Computing: A Comprehensive Review of Current and Future Applications

Claudiu BRANDAS, West University of Timisoara, Romania

Cosmin ENACHE, West University of Timisoara, Romania

Otniel DIDRAGA, West University of Timisoara, Romania

Andrei ALBU, West University of Timisoara, Romania

Abstract. Quantum Computing is currently a disruptive and game-changing technology that challenges the development of various industries, and it is a new paradigm in business software development. In this paper, we explore the current and future applications and research of quantum computing in the financial sector and present a SWOT analysis to evaluate its potential impact. We begin by introducing the fundamental concepts of quantum computing. Next, we analyze existing use cases and research on quantum computing in the financial sector. Finally, the SWOT analysis highlights the strengths, weaknesses, opportunities, and threats associated with implementing quantum computing in the financial sector. Our study emphasizes the transformative potential of quantum computing to reshape the financial sector by enabling faster processing, faster communication, better security, new financial services, solving complex problems, and more accurate decision-making processes. Quantum computing can significantly impact the following financial areas: portfolio optimization, risk management, option pricing, high-frequency trading, blockchain and cryptocurrencies, and AI applications (such as fraud detection and credit scoring).
Keywords: Quantum Computing, Financial Sector, SWOT Analysis


IoT, Mobile and Multimedia Solutions, Cybersecurity and Critical Infrastructures, Machine Learning Theory and Applications

1. An application of the Flexible Best Worst Method to Internet of Things

Constanta Zoie RADULESCU, National Institute for Research and Development in Informatics

Marius RADULESCU, “Gheorghe Mihoc-Caius Iacob” Institute of Mathematical Statistics and Applied Mathematics of the Romanian Academy

Abstract: Internet of Things (IoT) is an inter-device environment that has a significant role in many fields. A prioritization of the IoT security requirements represents an important element in the security evaluation of these systems. In this paper we propose a Flexible Best Worst Method (F-BWM), developed on the basis of the Best Worst Method (BWM) method. The input data in the F-BWM are the best criterion and the evaluations, in pairs, between a set of criteria and the best criterion. The number of comparisons, in the F-BWM is smaller than the number of comparisons in the BWM. An application of the F-BWM is made to the calculation of criteria weights for a set of IoT security requirements. A comparison of the results obtained with the help of F-BWM and BWM is realized. The criteria weights, calculated with the proposed method, can be used in multi-criteria methods for ranking a set of alternatives evaluated according to a set of criteria.

Keywords: Flexible Best Worst Method, Internet of Things, Criteria weights


2. Main Characteristics and Cyber Security Vulnerabilities of IoT Mobile Devices

Alisa HARKAI, Bucharest University of Economic Studies

Abstract: Nowadays, the Internet of Things (IoT) is present everywhere and is involuntarily changing the way we live and work in today’s society. Smart de-vices are becoming more prevalent, and the Internet is evolving to support their growing number. There are numerous benefits of IoT to the economy and businesses and the IoT adoption enables connectivity between devices, allowing for data processing and scalability of operations especially for businesses. IoT technology also provides businesses the tools and the protocols needed to de-sign and deploy smart solutions for various use cases, making like much easier for both businesses and users. However, the adoption of IoT comes with concerns over security and data privacy, requiring businesses to incorporate effective security measures to safeguard their systems. This article aims to emphasize how Internet of Things works, what are the fundamentals and characteristics of IoT and more important what are the strengths and weaknesses of this technology. Moreover, we want to see which are the security problems and vulnerabilities of this technology since it is rapidly evolving and affects and trans-forms the way we interact with devices and machines in our daily life.

Keywords: IoT devices, IoT characteristics, cybersecurity, vulnerabilities


3. An analysis about smartphone usage and security in Europe: trends and insights

Cosmin TEODORESCU, Bucharest University of Economic Studies

Abstract: The article examines the significance of trust, security, and privacy indicators associated with smartphones. It highlights that building trustworthy digital ecosystems is crucial to digital companies and society as a whole. The article reviews various studies conducted to investigate smartphone security, indicating that consumers lack proper security knowledge and make bad security decisions. It emphasizes that user-friendliness is critical to safeguarding users’ privacy, and the current privacy and security options on smartphones are challenging for many users to manage effectively. The methodology used for the study involves analyzing publicly available data from the Eurostat website. The article discusses the adoption of smartphones in the European Union, their reliance on accessing the Internet, and the levels of security by interpreting indicators like: percentage of smartphones that have some security system, installed automatically or provided with the operating system; percentage of individuals that have already lost information, documents, pictures or other kind of data on their smartphone as a result of a virus or other hostile type of programs; percentage of individuals that at least once restricted or refused access to personal data, when using or installing an app on the smartphone. The study aims to provide insights into the significance of trust, security, and privacy indicators related to smartphones.

Keywords: trust, security, privacy, smartphones, mobile operating systems


4. A Formal Intelligent Metric System for Measuring Cyber Security Maturity

Aurelian BUZDUGAN, Moldova State University

Gheorghe CAPATANA, Moldova State University

Abstract: This paper presents an innovative solution for enhancing cyber security in critical infrastructure. The proposed approach focuses on measuring cyber security maturity and identifying key risk areas through the use of a formal intelligent metric system. The system aims to assist the cyber security assessment process by com-paring the level of maturity against good practices or national requirements of critical infrastructure entities. The knowledge base of the formal intelligent metric system contains five maturity levels, which cover both technological and human dimension criteria. The system is universal for the field of critical infrastructure and helps increase the level of cyber security maturity while minimizing risks. The system can be used as a standalone solution or complement previously pro-posed decision support systems. Furthermore, it can be adapted to any type of critical infrastructure, depending on the context and requirements. This paper provides an overview and description of the formal intelligent metric system, dis-cusses its potential use cases in the critical infrastructure domain, and highlights possible adaptations given the context of each entity.

Keywords: Formal Intelligent Metric System, Cyber Security, Critical Infrastructure


5. Cyber Range User Effort Quantification Through Activity Monitoring Systems

Ionuț LATEȘ, Bucharest University of Economic Studies

Cătălin BOJA, Bucharest University of Economic Studies

Abstract: In the digital age, where cyberthreats are becoming more numerous and complicated, cybersecurity training has grown in importance. Cyber range systems offer a secure and regulated setting for cybersecurity training and education. These systems replicate real-world situations and give students practical practice defending against online threats. However, the capability of tracking trainee actions and giving them performance feedback is essential to the efficacy of cyber range training. The usefulness of cyber range systems in the training and learning process cannot be realized without the existence of a list of components capable of recording, analyzing and reporting the actions taken by trainees during the training period. The necessity of tracking student development as well as the ongoing need to improve the preset materials and scenarios within cyber range systems determine the necessity for these components’ inclusion.

Keywords: Cyber Range, Cyber-Security, Cyber Range IDS


6. Impact of personalization on improving a chatbot’s performance. Case study for a banking virtual assistant

Denisa Elena BALA, Bucharest University of Economic Studies

Stelian STANCU, Bucharest University of Economic Studies

Andreea PERNICI, Bucharest University of Economic Studies

Monica Ioana VULPE, Bucharest University of Economic Studies

Abstract: Virtual assistants have found their usefulness in a variety of fields and industries, their popularity increasing considerably in recent years. At the same time, the interest of businesses, but also of clients, in their use on a global level, has also developed. The financial-banking industry is a promoter of the adoption of virtual assistants, an important number of institutions in this field are calling for the use of chatbots in assisting clients with the aim of fulfilling their various needs. Digital banking has thus become a new normality, in line with the rapid technological progress. This paper analyzes the concept of personalizing a virtual assistant with basic functions in the banking field, in order to evaluate its performance. The evolution of the performance of the virtual assistant is thus studied under the influence of some changes through which it adapts to the user’s need and to the context in which he makes a certain request. The results indicate an improvement in the performance of the chatbot with its customization.

Keywords: Chatbot, NLP, personalization, virtual assistant, banking sector


7. A Citation-based Scientometric Analysis of Published Articles from Bucharest Academy of Economic Studies

Maria Ioana POPA, University of Craiova

Abstract: In this paper we deal with a scientometric analysis on a dataset that contains an indexed collection of citations counts and other metrics for the 1000 most cited scientific articles from the Bucharest Academy of Economic Studies, published between 2007 and 2022. Univariate and multivariate analyses are conducted to assess the international visibility of scientific publications, by capturing trends over the spanned period and structural or distributional characteristics in the data at hand. For the sake of clarity and ease of interpretation, the results were mostly summarized in a graphical form.

Keywords: Scientometric analysis, univariate methods, multivariate methods


8. Topic Modelling of Published Articles from Bucharest Academy of Economic Studies, based on Natural Language Processing

Ioana-Andreea GÎFU, University of Craiova

Abstract: Topic modeling is an unsupervised automatic learning technique based on natural language processing (NLP), which offers superior quality results and very high accuracy, thanks to using a combination of statistical methods and computational linguistics. This method is mainly used on a large corpus of data, on which we apply a set of advanced algorithms, with the aim of determining which topics are addressed within these documents and to classify them according to the topics detected. In this paper, we apply topic analysis and modelling to the abstracts of the 1000 most cited scientific articles from the Bucharest Academy of Economic Studies, published be-tween 2007 and 2022. First, we used n-grams models, which are probabilistic in nature, to visualize topics in the form of word clouds, searching for domain-specific topics, or for trends in topics over years. For more advanced topic modelling, we applied two well-known algorithms, namely Latent Dirichlet Allocation (LDA) and Non-Negative Matrix Factorization (NMF), allowing us to detect the most important topics, the article clusters associated with different topic mixtures, topic correlations, the inter-topic distance map, the most relevant topics for a given article etc.

Keywords: Topic modelling, Natural language processing, Wordclouds, n-grams


9. Ship Detection using SAR – an Integration of Geographic Systems

Ioana-Diana PETRE, Bucharest University of Economic Studies

Abstract: This paper presents an approach for ship detection in Port Constanta using Synthetic Aperture Radar (SAR) technology. The proposed methodology integrates several geographic systems, including Creodias API, Snap Desktop and ArcGIS Pro. A plugin has been developed for ArcGIS Pro that enables the download and preprocessing of raster images, as well as detecting the ships within the port using SNAPs built in Adaptive Thresholding and Object Discrimination methods. The integration of different geographic systems enables a more efficient and streamlined workflow for ship detection, as well as the potential for further analysis and visualization of the detected ships. The use of SAR technology also allows for detection in adverse weather conditions and at night, which can become a crucial factor for ship monitoring. The data regarding raster files is taken from the Amazon Sentinel-1 bucket which provides easy access to the Sentinel-1 satellite observation data, allowing users to quickly and efficiently process and analyze large amounts of information. In the scope of this paper data collection is a crucial step. After the raster images have been downloaded and preprocessed the identified targets are available within a shapefile and can then be loaded in a dedicated GIS application, such as ArcGIS Pro.

Keywords: Ship Detection, SAR, Adaptive Thresholding, Object Discrimination, GIS Integration


10. The Applicability of some Supervised Machine Learning Algorithms in End-stage Liver Disease

Oana VIRGOLICI, Bucharest University of Economic Studies

Horia-Marius VIRGOLICI, University of Medicine and Pharmacy “Carol Davila” Bucharest

Abstract: Model for end-stage liver disease (MELD) score, initially developed to predict survival following transjugular intrahepatic portosystemic shunt was subsequently found to be accurate predictor of mortality amongst patents with end-stage liver disease. Since 2002, MELD score using 3 objective variables (serum bilirubin, serum creatinine, and institutional normalized ratio – INR) has been used worldwide for listing and transplanting patients with end-stage liver disease allowing transplanting sicker patients first irrespective of the wait time on the list. Later, addition of serum sodium into the MELD score predicts waiting list mortality better than MELD alone. We propose models for predicting survival for patients with end-stage liver disease, using machine learning algorithms, such as Decision Tree, k-Nearest Neighbors and Logistic Regression, applying on a dataset of patients from Bucharest clinics for both MELD and MELD-Na scores. The features for train and evaluate the models are: institutional normalized ratio, serum creatinine, serum bilirubin for MELD-score and institutional normalized ratio, serum creatinine, serum bilirubin, serum sodium for MELD-Na score, respectively. We compare the performance of these algorithms in terms of accuracy score, f1 score and confusion matrix. The results obtained for both classification methods (applying MELD score and MELD-Na score, respectively) are satisfactory.

Keywords: MELD score, MELD-Na score, Machine Learning, Decision Tree, k-Nearest Neighbors, Logistic Regression


11. Develop a machine learning life cycle in Oracle Accelerated Data Science (ADS) SDK

Dimitrie-Daniel PLĂCINTĂ, Bucharest University of Economic Studies

Abstract: This paper initially described the advantages of the Oracle Accelerated Data Science (ADS) SDK in the larger context of OCI features. I will focus on ex-plaining the configuration steps for a machine learning life cycle. I will de-scribe the most important steps related to environment setup and clarify OCI and data science concepts. To test the features of ADS SDK, a public dataset on higher education students’ performance evaluation with 33 attributes and 145 rows was used. In have described and explained the most important steps for a machine learning pipeline with ADS SDK, completing with the features selected, based on machine learning explainability computing. The advantage of ADS SDK, Conda environments, can be further exploited in my next machine learning experiments.

Keywords: Oracle Accelerated Data Science, ADS SDK features, student prediction, regressor, machine learning explainability.



Florin Valeriu PANTELIMON, Bucharest University of Economic Studies

Bogdan Ștefan POSEDARU, Bucharest University of Economic Studies

Abstract: This paper analyzes the usage in programming of ChatGPT, a natural language processing tool, along with how it may enhance teamwork, communication, and code quality. ChatGPT is an effective tool for developers since it can produce code snippets, templates, and functions based on natural language input. The team’s capacity to grasp natural language input can assist closing the communication and cooperation gap between technical and non-technical team members. Furthermore, ChatGPT can assist developers in finding and fixing bugs or errors in their code more quickly and efficiently by increasing the accuracy of automated code review and testing. However, there are potential disadvantages to consider as well, such as the danger of relying too heavily on automated tools, restrictions on ChatGPT’s capacity to comprehend intricate technical concepts, and worries regarding bias in the training data used to create the tool. ChatGPT has the ability to change programming as a whole by making it more approachable, effective, and user-friendly. To ensure its usefulness and acceptance in the programming community, it will be necessary to carefully analyze and solve any potential constraints and difficulties.

Keywords: OpenAI, ChatGBT, programming, software development


13. General Characteristics of GPT-3 evaluation in Computer Science

Madalina PANA, Bucharest University of Economic Studies

Bogdan IANCU, Bucharest University of Economic Studies

Abstract: During the past years, the demand for programming skills has continued to grow, mainly due to the new technologies that are being implemented. This creates a great opportunity for professors, as computer science courses are, in this very moment, most-wanted in many universities. However, every teaching process has the same challenge, and that is grading the students. This part usually involves very much time invested in creating and verifying the students’ tests. However, today we have support from multiple technologies to automate this process and save the time that each professor is investing in this process. In this article, we explore how GPT-3 can help a professor evaluate a student’s test and give a grade for it. OpenAI is an artificial intelligence research organization that has made significant strides in natural language processing, computer vision, and reinforcement learning. Even though OpenAI released GPT almost 1 year ago, it is still an ongoing process to discover how artificial intelligence can help us automate our daily tasks. One of the key benefits of OpenAI is its ability to analyse and understand complex data sets quickly and accurately, which makes it an ideal tool for grading complex programming assignments. GPT can also help the professor write the tests, due to the powerful data which can access and use interpretation models. Once the test is created, the professor can use GPT to evaluate the student’s performance based on a set of requirements. GPT can analyse the student’s code and can also provide feedback on areas where they may be struggling.  Overall, this study contributes to the scientific literature by revealing mechanisms for using GPT to grade complex programming assignments in C++ object-oriented courses and reveals some of the positive effects that result from using this type of approach.

Keywords: testing, GPT, characteristics, automation.


14. Benefits and Challenges of Blockchain DAPPs in Education

Silviu OJOG, Bucharest University of Economic Studies

Paul POCATILU, Bucharest University of Economic Studies

Felician ALECU, Bucharest University of Economic Studies

Abstract: Blockchain technology has garnered significant attention across various industries due to its potential to revolutionize traditional systems through decentralization, transparency, and immutability. This paper explores the emerging trend of integrating blockchain-based decentralized applications (DApps) in the field of education. Educational institutions can achieve safe, secure, and transparent full management of student achievements, certifications, and credentials with the help of the blockchain distributed ledger system enabling students to build confirmable digital portfolios of securely stored and shared educational achievements relying on smart contracts and digital tokens. By leveraging the benefits and properly addressing the challenges of blockchain DAPPs in education, we can clear the way for a truly transformative learning experience era of tomorrow.

Keywords: Blockchain, Smart Contract, Security, Ethereum, Exploit, Immutability, Solidity


Quantitative Economics

1. Cybernetics Analysis of the Circular Economy from Romania

Nora CHIRIȚĂ, Bucharest University of Economic Studies

Irina GEORGESCU, Bucharest University of Economic Studies

Ionuț NICA, Bucharest University of Economic Studies, Banca Transilvania

Abstract: The circular economy can be defined from the perspective of an economic system as a system that aims to minimize the resources and energy consumed in a production process, by maximizing the value of products and materials through multiple life cycles. In this research, the Circular Economy in Ro-mania is analyzed from a cybernetic perspective, i.e. from the perspective of a complex adaptive system. The first part of the research approaches the stage of the transition from a linear economy to the circular economy in Ro-mania and the design of the cybernetic system of the circular economy. In the second part, the ARDL (Autoregressive Distributed Lag) model was used to examine the long-run and the short-run causality between renewable energy as a dependent variable and its determinants such as real GDP per capita, net greenhouse gas emission and others. The results highlight both the dependencies between renewable energy and macroeconomic factors, as well as emphasizing the inclusion of the circular economy in a cybernetic system.

Keywords: Circular Economy, Cybernetics Systems, Autoregressive Distributed Lag


2. Modeling Literary Preferences Using Complex Networks and Centrality Measures

Mioara BANCESCU, Bucharest University of Economic Studies

Ion Florin RADUCU, Bucharest University of Economic Studies

Abstract: For analyzing the preferences of consumers for certain types of literature, descriptive statistics is extensively used by both researchers and book readers. However, using only descriptive statistics methodology to interpret the individuals’ preferences to read novels, poems, short stories, theater or other book types is a limited approach. We suggest in this work using both descriptive statistics and node centrality measures of complex networks in order to better identify the books with the most influence over the preferences of a group of individuals. Using the software RStudio, a weighted undirected network is designed for the application of the study, by representing a group of individuals, their preferred books and the preference intensity. We present results and conclusions about representing individuals preferences using network structures, and about measuring most influential network nodes through centrality indicators: degree, closeness, betweenness and eigenvector centrality. Given that the book is a cornerstone of a civilized and educated society, we believe it should be more present among research topics, in order to encourage people (particularly young people) to read.

Keywords: Complex networks, Nodes centrality, Literature preferences, Undirected weighted graphs


3. Managing Tourism Crises: An MDP-based Approach for Optimal Investment Strategies

Emmanuel FRAGNIERE., University of Applied Sciences Western Switzerland, HES-SO Valais-Wallis

Francesco MORESION, University of Applied Sciences Western Switzerland, HES-SO Valais-Wallis

Abstract: Based on optimal control theory, we propose a model to determine the optimal allocation of resources between investment in production and prevention/mitigation measures, with the aim of maximizing the expected benefit in a mountain destination facing a crisis scenario. Specifically, we consider the case of a potential crisis caused by melting permafrost, leading to a landslide and the evacuation of tourists trapped in the resort. This problem can be formulated as a Markov decision problem (MDP). In this MDP, the decision maker has to choose the optimal action at each stage of the problem in order to maximize the expected benefit in the long run, considering the potential risks and losses associated with a crisis scenario. The transition probabilities between states depend on the current level of investment and risk, as well as the stochastic nature of permafrost melt and landslide risk. The expected rewards associated with each action depend on the current state and potential outcomes of the crisis scenario. The actions available at each stage of the problem include investment in production, investment in prevention/mitigation measures, or inaction. By solving this MDP, through a corresponding mathematical programming problem, we can determine the optimal investment strategy that maximizes the expected benefit while minimizing the risk in the face of a potential crisis caused by melting permafrost and the consequences for the mountain destination. A numerical experiment based on fictitious data is proposed to show how the method can be applied.

Keywords: Tourism crisis, Optimal stochastic control, Prevention/mitigation


4. Carbon emission reduction effect and influencing mechanism of OFDI and green credit under the “double-carbon” target

Peirong LI, Beijing Union University

Jinzhu ZHANG, Beijing Union University

Yong LI, University of International Business and Economics

Yuan TIAN, Beijing Union University

Abstract: Foreign direct investment (OFDI) is an important engine of economic growth. How to effectively exert its carbon emission reduction effect is the key to promote China’s high level opening up to the world and the realization of the “double carbon” goal. At the same time, the development of green finance helps to provide financial support for green and low-carbon enterprises OFDI, thus promoting green development of China’s outbound investment. However, few studies have revealed the impact mechanism of OFDI on China’s carbon emissions in the context of the “two-carbon” target, especially the regulatory role of green finance development on OFDI’s carbon emission reduction effect. Based on the panel data of 30 provinces in China from 2008 to 2020, this paper empirically analyzes the impact and mechanism of OFDI and green credit on carbon emissions in China. The results show that OFDI significantly reduces carbon emission intensity, with a 1% increase in OFDI leading to a 0.0508% decrease in carbon emission intensity, and the carbon emission intensity of the current period is positively influenced by the carbon intensity of the previous period. OFDI indirectly inhibits China’s carbon emission through promoting green technology progress and economic scale expansion. Green credit can strengthen the carbon emission reduction effect of OFDI, but the level of financial services weakens the effect of OFDI. On this basis, suggestions are put forward to enhance international exchanges and cooperation, rationally expand the economic scale, and continuously improve the level of green technology and green finance.

Keywords: OFDI, Green credit, Financial service level, Carbon intensity


5. Index Arbitrage Systematic Trading Strategy Value Proposition

Iosif ZIMAN, Tazlabs Ltd, Hong Kong

Abstract: Our value proposition is a high frequency index arbitrage systematic strategy that operates in the sub-second time frame- it takes decisions on all instruments universe in less than 100 milliseconds. The profits come from building intra-day positions of futures against partial baskets of stocks, locking in future’s fair value basis and benefiting from short term pricing anomalies in the stocks. It supports trading up to a USD 100 million turnover a day, with an average daily profit of 8bps. We would hence make a yearly Pnl of USD 20 million. And because it trades within a very short time frame based on the market micro-structure, we believe the strategy offers relevant diversification potential for a variety of asset managers and should generate a priori new uncorrelated results.

Keywords: index arbitrage, systematic trading strategy, high frequency


6. How Does Platform Labor Process Control Affect Courier’s Employment Mobility Intentions? — The Mediating Effects of Overtime Work and Job Autonomy

Bingbing ZHANG Beijing Union University

Yin YAO, Beijing Union University

Yu XIE, Beijing Union University

Xinyu WANG, Beijing Union University

Abstract: As one of the typical occupations in the new forms of employment generated by the platform economy, courier has become an important channel for workers to achieve employment and increase their income. The labor process control of courier by platforms has led to a decline in their employment experience and high mobility, which has affected the overall stability of employment. Using courier as the research target, a questionnaire survey was conducted to explore the influence mechanism of platform labor process control on employment mobility intentions and the heterogeneity of this influence mechanism among different types of workers. The results show that among the three elements of platform labor process control, algorithmic control, incentive control and evaluation control all have a significant positive impact on the employment mobility intentions of courier, with overtime work and job autonomy playing a partly mediating role respectively, job autonomy playing a significantly larger mediating role than overtime work, and part-time workers are more likely to be influenced by platform labour process control than full-time workers. On this basis, it provides a basis and reference for relevant government departments to implement effective regulation of platform enterprises, to control the degree of platform labour process control within a reasonable range, and to enhance the employment stability of workers.

Keywords: Platform labor process control, employment mobility intentions, courier


7. Investigating the European Union minimum wage setting mechanisms through the Directive (EU) 2022/2041

Georgiana STANCIULESCU, Bucharest University of Economic Studies

Madalina Ecaterina POPESCU, Bucharest University of Economic Studies

Abstract: Minimum wage is currently one of the most debated topics across economists, some claiming its negative implications on losing jobs, while others on dropping the poverty rate. Recently, the European Parliament and the Council adopted the Directive (EU) 2022/2041 on adequate minimum wages, with which the European Union countries will have to comply by 15 November 2024. The document aims to establish the framework and methodology to increase minimum wage threshold within European Union in order to achieve decent living and working conditions. Hence, this article aims to provide a clear overview on the Directive and to identify some examples of best practices on minimum wage setting mechanisms across European Union. Indicators on gross minimum wage, GDP per capita, unemployment rate and global gender gap index for the year 2022 were used in a country cluster analysis in order to identify some best practices across countries with more socio-economic similarities.

Keywords: Minimum wage, gender gap index, wage inequality, cluster analysis


8. A Quantitative Approach to Default Probability Estimation using the ZPP Model: a Study for LUNA and FTT Virtual Currencies

Nicolae SPATARU, Dell Technologies

Abstract: Considering the recent fears regarding virtual currencies, this study aims to evaluate the risk of their collapse in the context of information that is limited to the price. Since the future of many coins is in doubt, it is important for someone to figure out if they are worth buying. In this context, two currencies that collapsed were analyzed, namely LUNA and FTT (FTX token), the latter being associated with accounting fraud. For their analysis, a model proposed by Fantazzini et. al. (2007), Zero-Price Probability (ZPP) was used, obtaining very good results regarding the prediction of the probability of collapse for the FTX token and not concluding, but interesting findings regarding the LUNA coin. The data used covered a period of 2 or 3 years before the price crash (the data used stopped a few days before its accelerated decline). The results of the study show that the ZPP model is a good predictor, but with results that vary depending on the set parameters, and obviously a thorough analysis from several angles is needed to estimate the risks of a virtual currency.

Keywords: Cryptocurrencies, ZPP, Default, FTT, LUNA


9. Modeling the impact of Natural Gas and Oil Price Crisis on Inflation

Costin Radu BOLDEA, University of Craiova

Bogdan Ion BOLDEA, West University of Timisoara

Abstract: The paper proposes a comparative analysis of the influence of volatility spasms of the Gas and Oil market on Inflation for six European countries during the last two years. We attempted to measure the impact of Oil and Gas price variation on short-term Inflation Rates for the selected countries using a non-linear regression model, derived with the help of a genetic optimization algorithm.

Keywords: Inflation, Non-linear regression model, Genetic algorithm



Antolie BARACTARI, Academy of Economic Studies of Moldova

Ștefan BLANUȚA, Academy of Economic Studies of Moldova

Anatol GODONOAGĂ, Academy of Economic Studies of Moldova

Abstract: This paper addresses a production system management issue with a focus on optimizing hypothetical profit. The transportation costs of resources and goods are considered, along with the actual production process. The model aims to plan transportation efficiently to minimize costs and maximize profit, while also considering the environmental impact of production and transportation activities. It includes restrictions targeting harmful emissions to minimize environmental impact. Moreover, the model considers demand and supply, planning production based on market demand and production capacity. In summary, this holistic approach to production system management provides an efficient and sustainable way to plan and make decisions, optimizing profit while minimizing environmental impact.

Keywords: Production, transportation, pollution function, economic-mathematical model, profit optimization, decision making


11. Application of Artificial Intelligence techniques in the detection of Financial Bubbles

Ionuț NICA, Bucharest University of Economic Studies, Banca Transilvania

Adrian DOMENTEANU, Bucharest University of Economic Studies

Nora CHIRIȚĂ, Bucharest University of Economic Studies

Abstract: The Financial Market and Commercial Bank approached as cybernetic systems form the core of national and global economic systems, given their un-predictability and their sensitivity to any changes. Is it possible that the in-formation published by the European Central Bank may interfere with stock market developments or financial bubbles? This main hypothesis is the basis of this research. The texts that have been written in English by the European Central Bank between 2000-2022 were taken over and compacted according to the month and year in which they were published and feelings were extracted. In terms of stock market indicators, the 14 most important indices were taken over, 5 from Europe, 5 from North America and 4 from Asia which were transformed into monthly returns.   Using the VAR model, it has been shown a link between the change in the profitability of the DJIA stock market index and the subjectivity of the texts, the positive feeling felt, if there was a pandemic in the analyzed period and the profitability of the HSI index. The research showed that financial bubbles could be observed over a period of time, indicating a connection between European Central Bank texts, stock market indices and financial bubbles.

Keywords: Artificial Intelligence, Text Mining, Sentiment Analysis, Financial Bubbles