About

Dimitar Trajanov is a Visiting Research Professor at Boston University and the Head of the Department of Information Systems and Network Technologies at the Faculty of Computer Science and Engineering at Ss. Cyril and Methodius University in Skopje. He earned his Ph.D. from the University of Ss Cyril and Methodius. Trajanov served as the founding Dean of the Faculty of Computer Science and Engineering from March 2011 to September 2015, during which time the faculty became the largest technical faculty in Macedonia. He is also the leader of the Regional Social Innovation Hub established in 2013 as a cooperation between UNDP and his faculty. His professional experience includes roles such as Senior Data Science Consultant for a major pharmaceutical company, Data Science consultant for UNDP in North Macedonia, and software architect in several startups. Trajanov's research interests encompass Data Science and Machine Learning, Natural Language Processing, FinTech, Semantic Web, and Technology for Development and Climate Change. He has authored more than 170 journal and conference papers and seven books, and has been involved in over 70 research and industry projects, leading more than 40 of them.

Research topics

• Artificial Intelligence
• Computer Science
• Natural Language Processing
• Machine Learning
• Data science
• Theoretical computer science
• Programming language
• Economics
• Finance

Selected publications

• AI Agents in Finance and Fintech: A Scientific Review of Agent-Based Systems, Applications, and Future Horizons

  Computers, materials & continua/Computers, materials & continua (Print) · 2025-10-30 · 2 citations

  articleOpen accessSenior author

  Artificial intelligence (AI) is reshaping financial systems and services, as intelligent AI agents increasingly form the foundation of autonomous, goal-driven systems capable of reasoning, learning, and action. This review synthesizes recent research and developments in the application of AI agents across core financial domains. Specifically, it covers the deployment of agent-based AI in algorithmic trading, fraud detection, credit risk assessment, robo-advisory, and regulatory compliance (RegTech). The review focuses on advanced agent-based methodologies, including reinforcement learning, multi-agent systems, and autonomous decision-making frameworks, particularly those leveraging large language models (LLMs), contrasting these with traditional AI or purely statistical models. Our primary goals are to consolidate current knowledge, identify significant trends and architectural approaches, review the practical efficiency and impact of current applications, and delineate key challenges and promising future research directions. The increasing sophistication of AI agents offers unprecedented opportunities for innovation in finance, yet presents complex technical, ethical, and regulatory challenges that demand careful consideration and proactive strategies. This review aims to provide a comprehensive understanding of this rapidly evolving landscape, highlighting the role of agent-based AI in the ongoing transformation of the financial industry, and is intended to serve financial institutions, regulators, investors, analysts, researchers, and other key stakeholders in the financial ecosystem.

  PublisherDOI

• Aligning Food Ingredients with Multiple Semantic Resources

  Communications in computer and information science · 2025-01-01

  book-chapter
  PublisherDOI

• Ontology-Based Structuring and Analysis of North Macedonian Public Procurement Contracts

  ArXiv.org · 2025-05-14

  preprintOpen accessSenior author

  Public procurement plays a critical role in government operations, ensuring the efficient allocation of resources and fostering economic growth. However, traditional procurement data is often stored in rigid, tabular formats, limiting its analytical potential and hindering transparency. This research presents a methodological framework for transforming structured procurement data into a semantic knowledge graph, leveraging ontological modeling and automated data transformation techniques. By integrating RDF and SPARQL-based querying, the system enhances the accessibility and interpretability of procurement records, enabling complex semantic queries and advanced analytics. Furthermore, by incorporating machine learning-driven predictive modeling, the system extends beyond conventional data analysis, offering insights into procurement trends and risk assessment. This work contributes to the broader field of public procurement intelligence by improving data transparency, supporting evidence-based decision-making, and enabling in-depth analysis of procurement activities in North Macedonia.

  PublisherOA PDFDOI

• A Unified Framework for Alzheimer’s Disease Knowledge Graphs: Architectures, Principles, and Clinical Translation

  Brain Sciences · 2025-05-19 · 3 citations

  reviewOpen access

  This review paper synthesizes the application of knowledge graphs (KGs) in Alzheimer's disease (AD) research, based on two basic questions, as follows: what types of input data are available to construct these knowledge graphs, and what purpose the knowledge graph is intended to fulfill. We synthesize results from existing works to illustrate how diverse knowledge graph structures behave in different data availability settings with distinct application targets in AD research. By comparative analysis, we define the best methodology practices by data type (literature, structured databases, neuroimaging, and clinical records) and application of interest (drug repurposing, disease classification, mechanism discovery, and clinical decision support). From this analysis, we recommend AD-KG 2.0, which is a new framework that coalesces best practices into a unifying architecture with well-defined decision pathways for implementation. Our key contributions are as follows: (1) a dynamic adaptation mechanism that adapts methodological elements automatically according to both data availability and application objectives, (2) a specialized semantic alignment layer that harmonizes terminologies across biological scales, and (3) a multi-constraint optimization approach for knowledge graph building. The framework accommodates a variety of applications, including drug repurposing, patient stratification for precision medicine, disease progression modeling, and clinical decision support. Our system, with a decision tree structured and pipeline layered architecture, offers research precise directions on how to use knowledge graphs in AD research by aligning methodological choice decisions with respective data availability and application goals. We provide precise component designs and adaptation processes that deliver optimal performance across varying research and clinical settings. We conclude by addressing implementation challenges and future directions for translating knowledge graph technologies from research tool to clinical use, with a specific focus on interpretability, workflow integration, and regulatory matters.

  PublisherOA PDFDOI

• Evaluating Trustworthiness in AI: Risks, Metrics, and Applications Across Industries

  Electronics · 2025-07-04 · 39 citations

  articleOpen accessSenior authorCorresponding

  Ensuring the trustworthiness of artificial intelligence (AI) systems is critical as they become increasingly integrated into domains like healthcare, finance, and public administration. This paper explores frameworks and metrics for evaluating AI trustworthiness, focusing on key principles such as fairness, transparency, privacy, and security. This study is guided by two central questions: how can trust in AI systems be systematically measured across the AI lifecycle, and what are the trade-offs involved when optimizing for different trustworthiness dimensions? By examining frameworks such as the NIST AI Risk Management Framework (AI RMF), the AI Trust Framework and Maturity Model (AI-TMM), and ISO/IEC standards, this study bridges theoretical insights with practical applications. We identify major risks across the AI lifecycle stages and outline various metrics to address challenges in system reliability, bias mitigation, and model explainability. This study includes a comparative analysis of existing standards and their application across industries to illustrate their effectiveness. Real-world case studies, including applications in healthcare, financial services, and autonomous systems, demonstrate approaches to applying trust metrics. The findings reveal that achieving trustworthiness involves navigating trade-offs between competing metrics, such as fairness versus efficiency or privacy versus transparency, and emphasizes the importance of interdisciplinary collaboration for robust AI governance. Emerging trends suggest the need for adaptive frameworks for AI trustworthiness that evolve alongside advancements in AI technologies. This paper contributes to the field by proposing a comprehensive review of existing frameworks with guidelines for building resilient, ethical, and transparent AI systems, ensuring their alignment with regulatory requirements and societal expectations.

  PublisherOA PDFDOI

• Applicability Assessment of Technologies for Predictive and Prescriptive Analytics of Nephrology Big Data

  PROTEOMICS · 2025-05-27

  reviewOpen accessSenior author

  The integration of big data into nephrology research will open new avenues for analyzing and understanding complex biological datasets, driving advances in personalized management of kidney diseases. This paper describes the multifaceted challenges and opportunities by incorporating big data in nephrology, emphasizing the importance of data standardization, advanced storage solutions, and advanced analytical methods. We discuss the role of data science workflows, including data collection, preprocessing, integration, and analysis, in facilitating comprehensive insights into disease mechanisms and patient outcomes. Furthermore, we highlight predictive and prescriptive analytics, as well as the application of large language models (LLMs) in improving clinical decision-making and enhancing the accuracy of disease predictions. The use of high-performance computing (HPC) is also examined, showcasing its role in processing large-scale datasets and accelerating machine learning algorithms. Through this exploration, we aim to provide a comprehensive overview of the current state and future directions of big data analytics in nephrology, with a focus on enhancing patient care and advancing medical research.

  PublisherOA PDFDOI

• A Multi-Agent System for Semantic Mapping of Relational Data to Knowledge Graphs

  ArXiv.org · 2025-06-12

  articleOpen accessSenior author

  <p><strong>Proceedings of the 1st GOBLIN Workshop on Knowledge Graph Technologies</strong><br><em>Leipzig, Germany — June 12, 2025</em></p> <p>The 1st GOBLIN Workshop on Knowledge Graph Technologies was held in Leipzig, Germany, on June 12, 2025, as part of the activities of the GOBLIN COST Action.<br>The workshop brought together researchers, practitioners, and stakeholders to discuss advances in Knowledge Graph technologies, applications, and open challenges. See the full program of the workshop at <a href="http://dbpedia.org/events/goblin25-workshop/">http://dbpedia.org/events/goblin25-workshop/</a>.</p> <p>This record serves as the official proceedings of the workshop. All accepted papers are published individually in the <a href="https://zenodo.org/communities/goblin25-workshop/">1st GOBLIN Workshop community</a> on Zenodo and are listed below with their Digital Object Identifiers (DOIs).</p> <p> </p> <h3>Accepted Papers</h3> <ol> <li> <p><strong>A Multi-Agent System for Semantic Mapping of Relational Data to Knowledge Graphs</strong><br><em>Milena Trajanoska, Riste Stojanov and Dimitar Trajanov</em><br>DOI: 10.5281/zenodo.16911414</p> </li> <li><strong>A Visual Notation for Web-Based Ontology Modeling</strong><br><em>Julija Ovcinnikova and Karlis Cerans</em><br>DOI: 10.5281/zenodo.16911656</li> <li> <p><strong>Bridging the Gap Between Natural Language and Semantic Web: A Text-to-SPARQL System</strong><br><em>Dimitar Pavlovski and Riste Stojanov</em><br>DOI: 10.5281/zenodo.16912011</p> </li> <li> <p><strong>An Event-centered Knowledge Graph for Bulgaria</strong><br><em>Kiril Simov, Nikolay Paev and Petya Osenova</em><br>DOI: 10.5281/zenodo.16912113</p> </li> <li> <p><strong>AI Agent-Driven Framework for Automated Product Knowledge Graph</strong> <strong>Construction in E-Commerce</strong><br><em>Dimitar Peshevski, Riste Stojanov and Dimitar Trajanov</em><br>DOI: 10.5281/zenodo.16912163</p> </li> <li> <p><strong>Towards Generating Synthetic EHR Knowledge Graphs — a Probabilistic Approach</strong><br><em>Milos Jovanovik, Eva Milenkova, Maxime Jakubowski and Katja Hose</em><br>DOI: 10.5281/zenodo.16912250</p> </li> <li> <p><strong>Prompting or Fine-tuning? Evaluating Relation Classification in Portuguese for Knowledge Graph Construction</strong><br><em>Tomas Pinto, Bruno Ferreira, Catarina Silva and Hugo Goncalo Oliveira</em><br>DOI: 10.5281/zenodo.16912342</p> </li> <li> <p><strong>LLM-Powered Knowledge Graphs vs Topic Modelling for Sustainable Development Analytics</strong><br><em>Buket Fildisi, Edlira Vakaj, Amna Dridi and Atif Azad</em><br>DOI: 10.5281/zenodo.16912396</p> </li> <li> <p><strong>From LLM Generation to Knowledge Representation: Creating and Structuring the GeminiKnowledge-sr QA Dataset for Serbian</strong><br><em>Ranka Stankovic, Nikola Jankovic, Jovana Radenovic and Milica Ikonic Nesic</em><br>DOI: 10.5281/zenodo.16912469</p> </li> <li> <p><strong>The CK25 Corporate Knowledge Reference Dataset for Benchmarking Text 2 SPARQL Question Answering Approaches</strong><br><em>Sebastian Tramp and Rene Pietzsch</em><br>DOI: 10.5281/zenodo.16912605</p> </li> <li> <p><strong>Digitizing and Structuring Early Marine Biodiversity Records: A GraphRAG-</strong><strong>Based Methodology</strong><br><em>Gustavo Nunez, Marcos Zarate, Darıo Ceballos and Pablo Fillottrani</em><br>DOI: 10.5281/zenodo.16912811</p> </li> <li> <p><strong>Smart Learning Applications with the combination of the Open Research Knowledge Graph and Teaching Knowledge Graphs</strong><br><em>Eleni Ilkou and Soren Auer</em><br>DOI: 10.5281/zenodo.16912917</p> </li> <li> <p><strong>Towards personal data store-based retrieval augmented generation in mobile computing</strong><br>Zachary Grider and Alexander Nelson<br>DOI: 10.5281/zenodo.16913027</p> </li> <li><strong>Can Personal KG-based RAG Empower Patients?</strong><br><em>Mariana Dias and Carla Teixeira Lopes</em><br>DOI: 10.5281/zenodo.16913140</li> </ol> <p> </p>

  PublisherOA PDFDOI

• Author response for "Multiword Discourse Markers Across Languages: A Linguistic and Computational Perspective"

  2025-04-03

  peer-review
  PublisherDOI

• Author response for "Multiword Discourse Markers Across Languages: A Linguistic and Computational Perspective"

  2025-02-13

  peer-review
  PublisherDOI

• Benchmarking Sentence Encoders in Associating Indicators With Sustainable Development Goals and Targets

  IEEE Access · 2025-01-01

  articleOpen access

  The United Nations’ 2030 Agenda for Sustainable Development balances the economic, environmental, and social dimension of sustainable development in 17 Sustainable Development Goals (SDGs), monitored through a well-defined set of targets and global indicators. Although essential for humanity’s future well-being, this monitoring is still challenging due to the variable quality of the statistical data of global indicators compiled at the national level and the diversity of indicators used to monitor sustainable development at the subnational level. Associating indicators other than the global ones with the SDGs/targets may help not only to expand the statistical data, but to better align the efforts toward sustainable development taken at (sub)national level. This article presents a model-agnostic framework for associating such indicators with the SDGs and targets by comparing their textual descriptions in a common representation space. While removing the dependence on the quantity and quality of the statistical data of the indicators, it provides human experts with data-driven suggestions on the complex and not always obvious associations between the indicators and the SDGs/targets. A comprehensive domain-specific benchmarking of a diverse sentence encoder portfolio was performed first, followed by fine-tuning of the best ones on a newly created dataset. Five sets of indicators used at the (sub)national level of governance (around 800 indicators in total) were used for the evaluation. Finally, the influence of 40 factors on the results was analyzed using explainable artificial intelligence (xAI) methods. The results show that (1) certain sentence encoders are better suited to solving the task than others (potentially due to their diverse pre-training datasets), (2) the fine-tuning not only improves the predictive performance over the baselines but also reduces the sensitivity to changes in indicator description length (performance drops even by up to 17% for baseline models as length increases, but remains comparable for fine-tuned models), and (3) better selected training instances have the penitential to improve the performance even further (taking into account the limited fine-tuning dataset currently used and the insights from the xAI analysis). Most importantly, this article contributes to filling the existing gap in comprehensive benchmarking of AI models in solving the problem.

  PublisherDOI

Frequent coauthors

• Milos Jovanovik

  Saints Cyril and Methodius University of Skopje

  34 shared

• Sonja Filiposka

  Saints Cyril and Methodius University of Skopje

  33 shared

• Irena Vodenska

  Saints Cyril and Methodius University of Skopje

  28 shared

• Riste Stojanov

  Saints Cyril and Methodius University of Skopje

  26 shared

• Kostadin Mishev

  Saints Cyril and Methodius University of Skopje

  18 shared

• Igor Mishkovski

  16 shared

• Ljupčo Kocarev

  Saints Cyril and Methodius University of Skopje

  16 shared

• Maryan Rizinski

  Boston University

  15 shared

Education

• Ph.D.

  University “Ss Cyril and Methodius”