Prof. Jan Kozak
University of Economics in Katowice
Poland
jan.kozak@ue.katowice.pl

Prof. Mikhail Moshkov
King Abdullah University of Science and Technology
Saudi Arabia
mikhail.moshkov@kaust.edu.sa

Dr Przemysław Juszczuk
University of Economics in Katowice
Poland
przemyslaw.juszczuk@ue.katowice.pl

Dr Barbara Probierz
University of Economics in Katowice
Poland
barbara.probierz@ue.katowice.pl

Machine learning nowadays is considered a group of various methods used to solve the most complex real-world problems. Its usability is crucial in fields like medicine, finance, text mining, image analysis and more. Among the most prominent examples of machine learning-related methods, we can find ensemble methods, multicriteria evolutionary algorithms, deep learning in neural networks, and many more. We are particularly interested in subjects including various hybrid methods, extensions of existing methods, and novel knowledge representations, which could be effectively used in real-world applications. New methods, such as using the autoML approach, as well as explainable AI, are also key aspects of modern machine learning approaches.
The second aspect of this session is devoted to still growing number of data available for users. Concepts like big data and data streams still gaining more and more attention. Classical methods seem to give debatable efficiency among this type of data. Thus, we believe that there is a necessity for continuous improvements in the widely understood machine learning and hybrid systems. This session is dedicated to all these methods and their extensions for real-world data and applications. Because of the big volume of processed data, a modern approach using cloud-based resources is also a subject of our interest.
The MLRWD 2025 Special Session at the 17th International Conference on Computational Collective Intelligence Technologies and Applications (ICCCI 2025) is devoted to several machine learning tasks - such as classification, clustering, prediction, discovering the relationships between parameter values and the interactions between parts of the analyzed approaches in the context of optimization. We would like to offer an opportunity for researchers to focus especially on new methods related mostly to applications of machine learning in real-world applications.

The scope of the session includes, but is not limited to, the following topics:

• Theoretical framework for ensemble methods
• Ensemble learning algorithms: bagging, boosting, stacking, etc.
• Ensemble methods in clustering
• Diversity, accuracy, Swarm and Evolutionary algorithms and their applications
• Multicriteria optimization for large-scale problems
• Decision support systems
• Data classification and data clustering
• Decision trees and ensemble methods
• Stream data analysis
• Big Data representation
• Association rule mining
• Artificial neural networks and deep learning
• Contributions from similar subjects e.g. Computational Learning Models, Evolutionary Techniques, Multi-Agent
• Real-time and semi-real-time prediction services
• New methods of efficient data retrieval and storage in machine learning
• Explainable AI