Leveraging Artificial Intelligence, Knowledge Graphs and Multicriteria Approaches for Enhanced Decision-Making and Recommendation Systems

Dear Colleagues,

In the era of data-driven innovation, leveraging Artificial Intelligence (AI), Knowledge Graphs (KGs), and multicriteria decision-making (MCDM) has emerged as a powerful paradigm for enhancing decision-making and recommendation systems. AI plays a central role by enabling the extraction of knowledge from heterogeneous data sources, learning user preferences, and supporting adaptive and data-driven decision processes. Knowledge Graphs provide structured and semantically rich representations of entities, criteria, and their interrelationships, while MCDM offers a rigorous framework for evaluating, prioritizing, and optimizing alternatives under multiple, often conflicting criteria.

Knowledge Graphs provide structured, semantically rich representations of information, enabling the understanding of relationships between entities and supporting reasoning over complex datasets. When combined with AI, particularly machine learning, deep learning, and natural language processing, these systems can move beyond traditional data-driven approaches toward more intelligent, interpretable, and adaptive decision-support tools.

A special interest of this Special Issue is the integration of Multi-Criteria Decision Making (MCDM) principles within AI- and KG-driven systems. Real-world decision-making and recommendation scenarios typically involve multiple, often conflicting criteria, requiring structured approaches for evaluation, comparison, and selection. MCDM provides a comprehensive framework that encompasses both evaluation and optimization perspectives, enabling the identification of preferred alternatives under complex constraints and trade-offs.

The combination of AI, Knowledge Graphs, and recommendation systems opens promising research directions. Knowledge Graphs can represent decision contexts, alternatives, criteria, and their interdependencies in a transparent and semantically enriched manner, while AI techniques can support learning from data, adapting to dynamic environments, and uncovering hidden patterns. Integrating MCDM concepts into such systems contributes to improved consistency, interpretability, and robustness of decision-making and recommendation processes, while also enabling the incorporation of domain knowledge and contextual information.

This Special Issue invites contributions that address theoretical advances, practical implementations, and interdisciplinary applications of AI-powered knowledge systems enriched with multicriteria decision frameworks. Topics of interest include, but are not limited to, the following:

• Integration of Knowledge Graphs with machine learning and deep learning models;
• MCDM-based approaches in AI-driven decision support and recommendation systems;
• Hybrid multi-criteria approaches and group multicriteria methods;
• Multicriteria optimization and decision modeling in intelligent systems;
• Explainable AI (XAI) through structured and multicriteria reasoning;
• Evaluation and selection of a conversational AI assistant;
• Leveraging Artificial Intelligence in selection and decision problems;
• Context-aware and personalized recommendation techniques;
• Semantic reasoning, inference, and knowledge integration for decision support;
• Graph-based learning and representation techniques;
• Hybrid recommender systems leveraging structured and unstructured data;
• Evaluation and benchmarking of AI systems using multicriteria frameworks;
• Scalability, efficiency, and real-time processing of large-scale Knowledge Graphs;
• Ethical considerations, bias mitigation, and transparency in AI-driven decisions.

Application domains include (but are not limited to): industry, engineering, healthcare, cybersecurity, IoT, finance, e-commerce, smart cities, and education.

Dr. Constanta Zoie Radulescu
Dr. Radu Boncea
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• knowledge graphs
• leveraging artificial intelligence
• graph neural networks
• large language models (LLMs)
• semantic web
• ontology-based reasoning
• natural language processing
• multi-criteria decision making (MCDM)
• decision support systems
• recommender systems
• explainable AI (XAI)
• machine learning, deep learning
• federated learning
• multicriteria optimization