RFOS - Repository of Faculty of Organizational Sciences Univ. of Belgrade
Not a member yet
2871 research outputs found
Sort by
Measuring improvements of the education system in the COVID-19 pandemic – A case study of Serbia
Get PDFThe purpose of this paper is the comparative analysis of traditional education and e-learning by the application of key performance indicators. The general objective of the study is to indicate the advantages and disadvantages of traditional education and e-learning through the analysis and comparison of these two forms of education by applying defined key performance indicators. The research was carried out in 15 gymnasiums and vocational high schools in the Republic of Serbia, with a sample of 11.204 students (the school year 2018–19) and 11.251 students (the school year 2019–20). The results of the research and conducted comparative analysis presented in this paper indicate that e-learning during the COVID-19 pandemic has significant advantages over traditional education, such as a reduction in the percentage of students who were sent to the make-up exam and who did not complete the school year, a reduction of the number of imposed disciplinary measures and absences from classes per student at the end of the school year and an increasing percentage of excellent students at the school level at the end of the school year. Based on the results, recommendations for improving the education process by implementing e-learning in developing countries are proposed. This paper presents a valuable resource for educators and scholars in defining the elements that can improve student learning outcomes, motivation and satisfaction levels
Komparativna analiza ERP sistema: Microsoft Dynamics NAV i Odoo Community
No full textThe paper provides a detailed comparison between two widely used ERP systems, Microsoft Dynamics NAV 2017 and Odoo Community, focusing on their performance within a Project Management scenario. The goal of the research is to evaluate and contrast the functionalities, scalability, and customization capabilities of each system, particularly in relation to their suitability for project and service management. The paper emphasizes the significance of thoroughly assessing organizational requirements before selecting an appropriate ERP system, highlighting the crucial role of tailored decision-making in this process
Fostering Crowd-Based Open Innovations in Serbian Railways - Preliminary Readiness Assessment
No full textThis research addresses the possibilities of applying the concepts of open innovations and crowdsourcing to increase railway traffic safety. The goal is to propose an approach to developing IoT-based solutions through crowdsourcing, where various participants can contribute, and conduct a preliminary assessment study of readiness of students to participate. Crowdsourcing-based open innovations have already shown a great potential for the rapid development of new solutions, but the application in the context of improving railway traffic safety has not been fully explored yet. For piloting purposes, the authors have organized an open innovation project, where the students of the Faculty of Organizational Sciences, University of Belgrade, were provided an opportunity to propose and develop solutions for various safety problems in railways. The solutions were expected to include one or both aspects of developing marketing plans for raising awareness and designing and prototyping the IoT solutions for the selected problem. Research results show students' general interest in participating in this type of project and provide implications regarding the organization of this type of project
Modelling Predictability of Airbnb Rental Prices in Post COVID-19 Regime: An Integrated Framework of Transfer Learning, PSO-Based Ensemble Machine Learning and Explainable AI
No full textIn this research, an effort has been put to develop an integrated predictive modeling framework to automatically estimate the rental price of Airbnb units based on listed descriptions and several accommodation-related utilities. This paper considers approximately 0.2 million listings of Airbnb units across seven European cities, Amsterdam, Barcelona, Brussels, Geneva, Istanbul, London, and Milan, after the COVID-19 pandemic for predictive analysis. RoBERTa, a transfer learning framework in conjunction with K-means-based unsupervised text clustering, was used to form a homogeneous grouping of Airbnb units across the cities. Subsequently, particle swarm optimization (PSO) driven advanced ensemble machine learning frameworks have been utilized for predicting rental prices across the formed clusters of respective cities using 32 offer-related features. Additionally, explainable artificial intelligence (AI), an emerging field of AI, has been utilized to interpret the high-end predictive modeling to infer deeper insights into the nature and direction of influence of explanatory features on rental prices at respective locations. The rental prices of Airbnb units in Geneva and Brussels have appeared to be highly predictable, while the units in London and Milan have been found to be less predictable. Different types of amenity offerings largely explain the variation in rental prices across the cities
Mediated Effect of Entrepreneurial Education on Students' Intention to Engage in Social Entrepreneurial Projects
No full textSocial enterprises are gaining great importance, since they can efficiently solve social problems and help reduce unemployment. Thus, it is important to discover how social entrepreneurial intention (SEI) can be enhanced. In this paper, a model of the impact of entrepreneurial education (EE) on SEI is formulated by relying on the human capital theory. It is hypothesized that EE acts on SEI directly as well as indirectly by increasing the perceived importance of social entrepreneurship (PISE). The model was evaluated on a sample of 400 students from the Republic of Serbia, and Bosnia and Herzegovina. The analysis was conducted using partial least squares structural equation modelling (PLS-SEM). In addition, a multigroup analysis was conducted in order to establish differences in the proposed relationship between countries. The obtained results indicate a positive impact of EE on SEI and a positive impact of PISE on SEI in both observed countries. The influence of EE on PISE, as well as the indirect effect of EE on SEI through PISE, was confirmed in Serbia, but not in Bosnia and Herzegovina. The results of this paper justify further government investment in the development of educational programs. This paper also gives recommendations to universities, educators, and researchers
Investigation of the brain carcinoma based on generalized variation coefficient similarity measures using complex q-rung orthopair fuzzy information
No full textBrain carcinoma is one of the massive dangerous diseases in the human body, and certain intellectuals have been affected by them. Additionally, by using the complex q-rung orthopair fuzzy set, which is the massive important, and dominant technique to manage indeterminate and ambiguous information in genuine life troubles. This study aims to employ the principle of variation coefficient similarity measures and generalized variation coefficient similarity measures under the complex q-rung orthopair fuzzy sets and illustrated their properties. Certain special cases of the elaborated measures are investigated to expand the superiority of the investigated works. Moreover, by using the presented generalized variation coefficient similarity measures under the complex q-rung orthopair fuzzy information, a medical diagnosis is illustrated to determine the most dangerous sorts of brain carcinoma in the human body to determine the supremacy and dominance of the elaborated measures. Lastly, certain examples are illustrated based on proposed measures under a complex q-rung orthopair fuzzy set to find the advantages and sensitive analysis of the initiated measures to illustrate the rationality and dominance of the developed measures
Knowledge Representation for Hierarchical and Interconnected Business Contexts
No full textAlthough business context has been introduced as an important concept for message-standards usage and maintenance, its usability depends on the technique used to represent contextual knowledge. This paper investigates a logic-based business-context-modeling technique, which is an alternative technique that can overcome some of the issues identified and discussed in this paper. For other issues, we propose future research directions
Time series analysis of Airbnb house rentals price in the Balkan region
No full textShared accommodation is one of the most recognizable business models of sharing economy.
Shared accommodation enables residents to temporarily rent out their properties to others through
online platforms for a predetermined price and for a defined period of time. One of the factors which impact the success of the business model is the daily rental price. The research question we raise in this study is related to daily housing rentals price prediction of Airbnb properties. In our case study, we used ARIMA modelling to model and predict housing rentals prices of the properties listed on the Airbnb platform in Ljubljana, Slovenia and Zagreb, Croatia
Toward the utilization of chatbots in the banking sector
No full textThe increasing interest in artificial
intelligence led many industry sectors to incorporate
this technology in order to remain competitive. The
integration of artificial intelligence chatbots in the
banking sector has brought significant changes. While
chatbots offer efficiency and convenience, they also
have limitations in handling complex situations. This
research examines the impact of chatbot technology in
the banking sector, specifically its application for
client communication, and assistance in banking
activities. To analyze chatbot capabilities, two use
case scenarios are defined, representing real banking
services of varying complexity and human involvement.
SWOT analysis was used to explore the benefits and
limitations of the chatbot application