Jelica Protic

This paper presents a comprehensive evaluation of the performance of large language models (LLMs) on a newly created set of 50 tasks in financial mathematics, with a focus on bond valuation. Models o3, Claude Opus 4, DeepSeek-R1, and Gemini were tested on three types of tasks (practical, real-life, and theoretical) and three difficulty levels (easy, medium, and hard). Model o3 achieved the highest average accuracy (80.9%), while DeepSeek-R1 showed the weakest results (70.6%). The detailed analysis included error classification (methodological, numerical, conceptual), measuring solution time as well as the application of ANOVA and post-hoc tests, which confirmed statistically significant differences between the models. The results indicate that more complex and theoretical tasks remain challenging for all models. The proposed methodology and the set of created tasks provide a basis for further research and for the development of specialized LLM systems for financial analysis and educational purposes.

Computational complexity analysis plays an essential part in the education of computer and software engineers. For that reason, it is carefully studied in programming courses, as well as in the algorithms and data structures courses. The number of students who learn programming is rapidly growing, but the number of teachers cannot keep up with that trend. Therefore, it is necessary to develop tools that can ease and accelerate the daily tasks of teachers, especially for learning purposes and in the context of automating the processes of exam preparation. We propose a novel template- and rule-based approach and a corresponding software system for assembling synthetic source code segments of defined time complexity. Based on the developed grammar, the system can produce source code segments with a broad scope of different time complexities while guaranteeing the complexity of the generated segment. The system can be used for generating questions for exams as it can assemble a large number of different code segments that can be given as questions that have similar difficulty levels. The system was evaluated both by human experts and ChatGPT tool.

The number of published scientific paper grows rapidly each year, totaling more than 2.9 million annually. New methodologies and systems have been developed to analyze scientific production and performance indicators from large quantities of data available from the scientific databases, such as Web of Science or Scopus. In this paper, we analyzed the international scientific production and co-authorship patterns for the most productive authors from Serbia based on the obtained Web of Science dataset in the period 2006–2013. We performed bibliometric and scientometric analyses together with statistical and collaboration network analysis, to reveal the causes of extraordinary publishing performance of some authors. For such authors, we found significant inequality in distribution of papers over journals and countries of co-authors, using Gini coefficient and Lorenz curves. Most of the papers belong to multidisciplinary, interdisciplinary, and the field of applied sciences. We have discovered three specific collaboration patterns that lead to high productivity in international collaboration. First pattern corresponds to mega-authorship papers with hundreds of co-authors gathered in specific research groups. The other two collaboration patterns were found in mathematics and multidisciplinary science, mainly application of graph theory and computational methods in physical chemistry. The former pattern results in a star-shaped collaboration network with mostly individual collaborators. The latter pattern includes multiple actors with high betweenness centrality measure and identified brokerage roles. The results are compared with the later period 2014–2023, where high scientific production has been observed in some other fields, such as biology and food science and technology.

A selection of Computer Science, Informatics or similar study programs for academic studies evidently becomes an emerging choice of a vast number of students in recent years. To address some of the open questions, we performed an 25 empirical study based on a survey, with a goal to find out the main motivating fac tors directing students to select computer science, informatics or similar programs for studying in a much greater extent. The survey was conducted on a sample of 1517 students from five well established, and most traditional faculties of computer science and informatics at three largest university cities in Serbia: Belgrade, Novi Sad, and Nisˇ. The created sample is representative enough to illustrate the current situation and trends common for many similar societies. Our first analyses show that the main motivating factor to select computer science or informatics study program at all faculties is a students’ motivation to study just that topic, while at management faculty it is significantly less important. However, we also noticed that significant number of students wished to study something else but chose computer science and informatics due to possibility of finding jobs easier and of earning higher salaries in industry. The most important influential factors to choose a computer science or informatics major come from family members, and close relatives. The perceived brand and reputation of a faculty also plays a significant role. Students being examined prevalently tend to be satisfied with the faculty they have chosen. However, many of them see themselves leaving the country in a near or far future.

IT education is very important and a lot of effort is put into the development of tools for helping students to acquire programming knowledge and for helping teachers in automating the examination process. This paper describes a prototype of the program segment assembling software used in the context of making tests in the field of algorithmic complexity. The proposed new program segment assembling model uses rules and templates. A template is a simple program segment. A rule defines combining method and data dependencies if they exist. One example of program segment assembling by the proposed system is given. Graphical user interface is also described.