International Workshop
Advances & Challenges in Computing (A2C)
A Regular meeting
Date: 24 September 2025 (Wednesday)
Time of event: 18:00-20:00 (East European time, Kyiv)
Place: online
Email: a2c.wokshop@gmail.com
AGENDA:
- Speaker: Vitaliy Kobets
- Speaker: Vladyslav Iatsiuta
- Information about research projects and conferences: Anatoliy Sachenko
- Speaker: Vitaliy Kobets
(Prof., Dr. Sc. (Economics))
Professor of Computer Science and Software Engineering Department,
Kherson State University)
E-mail: vkobets@ksu.ks.ua
Topic: Application of RFM-D Analysis for Customer Segmentation Using
Machine Learning
Presentation in Ukrainian
Abstract: The research uses modern machine learning methods to apply RFM-D (Recency, Frequency, Monetary, Diversity) analysis for customer segmentation. The authors focus on integrating three main approaches: reinforcement learning methods, unsupervised, and supervised ML methods. The first approach, based on reinforcement learning, allows for adaptive adjustment of segmentation strategies based on variable customer characteristics and preferences and can continuously improve the process of selecting optimal strategies to achieve the objective function, which is important for businesses operating in a dynamic market environment. For unsupervised learning, the K-means method helps identify more homogeneous customer groups based on their characteristics, allowing businesses to customize their unique customer offers. At the same time, machine learning methods, such as classification algorithms, can predict customer behavior based on training data, ensuring high prediction accuracy and improving the quality of management decisions for each customer segment. The study results show that combining these approaches allows for effective customer segmentation and optimized customer interaction, critical for increasing loyalty and overall efficiency of business strategies.
Resume: In 2002, Vitaliy Kobets graduated with honors from Kherson State University. In 2008, he defended his PhD thesis specializing in mathematical methods and information technologies in supply chains. In 2019, he defended his Doctoral Thesis, which focused on the evolutionary and experimental modeling of microeconomic systems. In 2021, he was awarded the academic title of Professor of Informatics, Software Engineering, and Economic Cybernetics Department. His major research fields are evolutionary microeconomics, robo-advisors, business analytics, machine learning, and financial technology. Since 2002, he has been working at Kherson State University and has risen from Assistant Professor to Professor. In 2011-2020, he was a Deputy Head of Informatics, Software Engineering, and Economic Cybernetics Department; in 2019-2020, he was a Head of Education Quality Assurance Department; in 2020–2021, he was a Vice Rector for Academic Affairs. Since 2019, he has been a Professor of Computer Science and Software Engineering Department at KSU.
He has published over 80 peer-reviewed publications in international journals and conferences, indexed by Scopus and WoS.
Research interests include robo-advisors and investor portfolio optimization, factors influencing ICT adoption in SMEs, household food security and insecurity dynamics, and innovative data processing and analysis systems.
He is a member of the International Association for Technological Development and Innovations IATDI, a permanent specialized academic council member (Kyiv), a member of 3 editorial boards, a program committee member of international conferences, and a reviewer for international journals.
- Speaker: Vladyslav Iatsiuta
(Postgraduate student, Kherson State University)
E-mail: vladyslav.yatsiuta@university.kherson.ua
Topic: Multimodal NLP Techniques for Processing Unstructured Financial Information
Presentation in Ukrainian
Abstract: The research investigates the application of Natural Language Processing (NLP) tools for processing unstructured business data and automating the analysis of financial video content. A system architecture is proposed to transform different data types into a unified text format. An experimental study using ChatGPT-4o demonstrates that NLP models can accurately extract stock-related forecasts and risk assessments from YouTube videos, significantly improving investment decision-making speed and quality. The results confirm the potential of AI-based technologies for enhancing financial analytics and business data processing.
Resume: Vlad Iatsiuta received his Master’s degree in Informatics from Kherson State University in 2010 and his Master’s degree with honors in Information Systems and Technologies in 2023. From 2008 to 2010, he worked as a developer at the Laboratory of Integration of Pedagogical Software. Since 2010, he has been working at DataArt, where he has advanced to the positions of Senior Software Developer, Team Lead, and Architect. He has over 15 years of professional experience in software development across various business domains, including travel, finance, and healthcare.
He is a postgraduate student in software engineering at Kherson State University, conducting research in artificial intelligence, financial report generation, and business request processing. He has authored four publications in peer-reviewed journals indexed by Scopus and Web of Science.
His research interests include artificial intelligence applications in business analytics, financial technologies, and intelligent systems for data processing and decision support.
- Information about research projects and conferences: Anatoliy Sachenko
Doctor of Technical Sciences, Professor, scientific advisor of Research Institute for Intelligent Computer Systems.
E-mail: as@wunu.edu.ua