Multi-criteria decision-making methods conventionally rank alternatives by aggregating normalized criterion values into a composite score, an approach that depends on the normalization scheme, requires externally determined criterion weights, and evaluates performance in absolute terms without accounting for inter-criteria dependencies. This paper proposes machine learning-based Peer-Prediction Trees for multi-criteria decision-making, a novel method that ranks alternatives by their excess performance over data-driven peer expectations. For each criterion, a leave-one-out cross-validated decision tree predicts each alternative’s value from its performance on all other criteria; the residual between observed and predicted values extracts how much the alternative outperforms the empirical trade-off structure constraining its peers. Residuals are standardized, aligned with the preferred criterion direction, and aggregated into an Excess Performance Index using uniqueness-based weights derived endogenously from the cross-validated predictive fit. The method is validated on three real-world datasets: a numeric vehicle selection problem (22 alternatives, five criteria), a fully linguistic financial performance evaluation of Turkish listed firms (32 alternatives, four criteria), and a mixed numeric-linguistic exchange-traded fund selection problem (12 alternatives, nine criteria). The contributions of this work are fourfold: (1) the introduction of peer prediction via leave-one-out cross-validated decision trees as a multi-criteria decision-making ranking paradigm that evaluates excess performance rather than absolute scores; (2) a uniqueness-based criterion weighting scheme embedded into the method, eliminating the need for separate weighting procedures; (3) native handling of numeric, linguistic, and mixed decision matrices within a single unified framework; and (4) empirical validation across three heterogeneous real-world applications demonstrating the method’s versatility and interpretability.

Human resource management today, in an era of rapid technological achievements and a changing work environment, represents a great challenge. Particular attention is being directed toward the digitalization of business operations and technically modern management, while human resources still remain in the background. Teamwork, adaptability to new circumstances and quick response to problem-solving are the central part of this paper. The aim of the paper is to conduct an integrated performance evaluation of utility vehicle crews that collect and transport waste in the city of Doboj (Bosnia and Herzegovina) on a daily basis, using multi-criteria decision-making (MCDM) methods. Five crews (each crew consists of a driver and two support workers) work daily to keep the city clean while properly disposing of municipal waste. The selection of the best-ranked utility vehicle crew for the month of March 2026 was carried out using the FUCOM (Full Consistency Method) and MARCOS (Measurement Alternatives and Ranking according to COmpromise Solution) methods. The FUCOM method was used to determine the weights of nine influential criteria, while the MARCOS method was applied to rank five alternatives of utility vehicle crews. The research results showed that alternative A3 was ranked as the best-rated crew in the observed period, achieving the highest value of the utility function f(K3) = 0.878. The value f(K4) = 0.433 belongs to the worst alternative (A4) and represents the lower reference value within the MARCOS model.

This study aims to develop a novel Multi Criteria Decision Making (MCDM) methodological model for use as a decision support tool in industrial machine selection problems. To this end, a new integrated MCDM model consisting of Logarithmic normalization and Standard Deviation (LOGSTA), Logarithmic Percentage Change-driven Objective Weighting (LOPCOW), Logarithmic Decomposition of Criteria Importance (LODECI), and Evaluation by Distance from Ideal Solution of Alternatives (EDISA) methods has been designed for a real-world lathe selection problem faced by a manufacturing company in Turkiye. The criterion weights obtained according to the three methods (LOGSTA, LOPCOW, and LODECI) were combined, and the combined criterion weights were transferred to the EDISA method to create an alternative lathe ranking. According to the combined criterion weights, the criterion with the highest importance level was failure frequency (C1), while the criterion with the lowest importance level was active working time (C5). According to the ranking obtained as a result of transferring the combined criterion weights to the EDISA method, the lathe with the highest performance was determined to be Doosan PUMA VT 900 (A2), while the lathe with the lowest performance was determined to be Doosan Puma 300 LM (A1). The comparison analysis shows that the EDISA method produces the same rankings as the ARAS, COPRAS, and RAWEC methods. It is believed that this framework enables manufacturing managers to compare acquisition cost, reliability, operating characteristics, and resale value within a transparent decision process.

Improving pedestrian safety at urban intersections is a key challenge for achieving safer and more sustainable urban transport systems. This study develops a multi-criteria decision-making model (MCDM) for selecting the most appropriate traffic signal type at pedestrian crossings in different urban zones. Traffic conditions, illegal pedestrian crossings and the number of traffic accidents were taken into account during the modelling, as well as the characteristics of the urban environment. The research involved 66,616 pedestrians at 22 pedestrian crossings located in three urban zones: school zones, central zones, and non-central zones. The data were aggregated using Bayesian (beta-binomial) and classical statistical methods. The OPA-Group method was then used to develop the model. In the decision-making phase, the Ordinal Priority Approach (OPA) was applied as the core MCDM method. It was then extended to the OPA-Group framework to incorporate group-based evaluation in accordance with the model requirements. Additionally, a comprehensive sensitivity analysis was conducted, confirming the robustness and stability of the proposed model. The results show that traditional traffic signals are most suitable for school and non-central zones, whereas countdown traffic signals are recommended for central zones. Push-button traffic signals were identified as the least efficient solution for regulating pedestrian movement at pedestrian crossings.

This article enables preventive engineering and the risk of negative occurrences in the transport and temporary parking of vehicles with dangerous goods can be reduced, thus decreasing interactions with other traffic participants. An important element in transporting dangerous goods is defining suitable locations where these vehicles can be safely parked. The research, which consists of several phases, has been carried out along a highway network of approximately one thousand kilometres in length. Out of 95 potentially acceptable locations, 28 have been selected (for both directions) as the most suitable. In the first part of the research, a fuzzy Z multi-criteria decision-making (MCDM) model has been created to select the most suitable locations, followed by the formation of a total of 32 scenarios (16 for each direction), integrating the fuzzy PIvot Pair-wise RElative Criteria Importance Assessment (PIPRECIA) method with Z-numbers with a Geographic Information System (GIS) model. Such integration represents an original and unique model. Fuzzy MCDM model based on Z numbers enables more accuracy in defining the assessment of criteria due to considering probabilities of a given assessment. When evaluating the formed scenarios, a minimum distance between two adjacent locations has been taken into account, and it is 50 km. The obtained results show most suitable scenario S3 = S4 = 35.278 for the first direction, and S2 = S10 = 35.521 for the second direction. Sensitivity analysis through 24 sets shown that a few scenarios can be candidate for implementation depending from significance of criteria. The contribution of this article lies in its pioneering research of this kind and provides recommendations to relevant state authorities for implementing the best scenario, but final implementation depends from representative entities.

In conditions where information and communication technologies (ICT) dictate the “rules” of the market, the strong promotion and development of innovation-oriented small and medium-sized enterprises (SMEs) are essential. The transition from a traditional, linear system of waste management and fleet management in utility companies to a digital and circular-oriented system represents not only a significant challenge