This study proposes a machine learning framework to support risk‑based verification of expenditure declarations in European Structural and Investment Funds, reflecting the current regulatory emphasis on proportional and data‑driven audit strategies. Quantitatively, the problem is formulated as an imbalanced three-class classification task with ordered outcomes on high-dimensional administrative data; the ordinal structure is exploited ex post in evaluation and error interpretation. The framework classifies expense documents as validated, partially validated, or not validated, and provides audit authorities with interpretable probability estimates for each case. A predictive model was trained and validated on more than ninety thousand expense documents from the Italian Regional Operational Programme co‑funded by the European Regional Development Fund (2014–2020). Methodological challenges—ordered outcomes, severe class imbalance, and mixed‑type features—were addressed through targeted preprocessing and the CatBoost gradient‑boosting algorithm. The model achieved satisfactory predictive performance, offering probabilistic outputs aligned with the ordered structure of audit outcomes. Variable‑importance analysis confirmed the relevance of both financial and administrative variables in predicting irregularities. The framework is designed with operational integration in mind and could underpin risk‑based sampling in expenditure verification, subject to further validation across time, programmes, and beneficiary structures. Departing from a literature that largely focuses on binary classification or fraud detection, the study addresses the understudied challenge of multi‑class prediction in public expenditure control and provides an interpretable prototype decision‑support tool. The model could support public authorities in prioritizing controls and allocating resources more efficiently, contributing to the modernization of European Union fund management and promoting data‑driven, proportionate oversight—conditional on governance arrangements and external validation.

An essential role in any firm is human resource management, or HRM, with effective matching of employees to suitable positions remaining the main employment issue. Traditional methods often rely on simplistic data models, which fail to fully capture the complex relationships between employee attributes, job requirements, and performance outcomes. To overcome these issues, this manuscript is proposed. This manuscript presents a novel approach, Hierarchical Dilated Parrot Causal Convolutional Attention Networks (HieDil-P2CAN), designed to enhance human resource recommendations. The input dataset, titled “human resource recommendations,” contains synthetic employee data generated for comprehensive HR analysis. Preprocessing is performed using the Fuzzy Min–Max Neural Network. The technique creates regular presentations of data that are easy to understand. Feature extraction is achieved through the Q-value Regularized Transformer, which captures the critical attributes influencing job matching. The prediction phase employs the HieDil-P2CAN, integrating Dilated Causal Convolution Networks with Hierarchical Attention Models and optimized using the Parrot Optimizer to effectively predict and recommend the best human resource solutions. The framework demonstrates an impressive 99.4% accuracy, optimizing human resource recommendations by accurately matching employees to suitable jobs based on their skills and performance metrics. This results in improved employee satisfaction and organizational efficiency. The system also significantly reduces computational time and enhances the precision of HR decision-making processes.

Abstract Previous research highlights the impact of nonverbal cues and visual layouts on respondents’ interpretations and answers to survey questions (Schwarz et al. in Pub Opin Q 55(4):570–582, 1991; Tourangeau et al. in Pub Opin Q 71(1):91–112, 2007; Toepoel and Dillman in Soc Sci Comput Rev 29(2):193–207, 2011). In this study, we investigate the effect of numerical values on responses to five questions measured using 11-point bipolar scales. These questions asked for evaluations of the general impact of climate change and its effects on different groups. Respondents were randomly assigned to scales ranging from 0 to 10, or from − 5 to + 5. The scales were presented horizontally and had identical verbal endpoints anchored as “extremely negative” and “extremely positive”. The experiment was embedded in a cross-national face-to-face survey conducted in Hungary, Portugal, and Great Britain. Contrary to prior research (Schwarz et al. in Pub Opin Q 55(4):570–582, 1991; O’Muircheartaigh et al. J Off Stat 11:295–308, 1995; Tourangeau et al. in Pub Opin Q 71(1):91–112, 2007), our analyses show an opposite trend: the means tend to be consistently and significantly lower for the − 5/+5 scale. The discrepancy between our findings and previous studies suggests that the interpretations of the 0/10 and − 5/+5 scales could be item specific. The implications of these findings and how they fit with previous work are discussed.

The study seeks to examine the barriers to climate change awareness and education in Zimbabwe, using a hybrid Structural Equation Modelling (SEM) and Extreme Gradient Boosting (XGBoost). The results revealed a positive link between media coverage, climate data accessibility, environmental education, stakeholder engagement, and technological advancement with the dissemination of information, except for public perception through SEM. The perception of the public had a negative beta value, highlighting the urgent need for education. Dissemination of information was identified as the principal barrier to climate awareness and education using the XGBoost model, whilst climate data accessibility was identified as the least important. Key contributions of the study include uncovering emerging trends, the development of a new theoretical framework, generation of effective and significant insights for policymakers and governments in their quest to improve climate awareness and education, and provision of guidelines for actions to reduce climate change.