Abstract
Data-driven decision models based on Artificial Intelligence (AI) are increasingly adopted across domains. However, these models are susceptible to bias that can result in unfair or discriminatory outcomes. Recent research has explored causal discovery methods as a promising way to understand and improve fairness in decision-making systems. In this work, we investigate how different conditional independence tests used in constraint-based causal discovery algorithms, specifically the PC algorithm, affect fairness and performance. We perform an empirical evaluation on several datasets, including Portuguese public contracts, COMPAS, and the German Credit dataset. Using seven conditional independence tests, we assess model behavior under fairness (demographic parity, accuracy parity, equalized odds and predictive rate parity) and performance (accuracy, F1-score, AUC) metrics. Our findings reveal that some tests, due to their statistical properties, fail to expose unfairness detectable via causal structures, even when performance metrics appear acceptable. Furthermore, we highlight significant differences in computational efficiency among the tests, with x2-Adf, sp-mi, and sp-x2 being the least efficient. This study underscores the need for careful selection of conditional independence tests in causal discovery to ensure both fairness and reliability in data-driven decision systems.

Abstract

Abstract
Detecting anomalies in Waste transportation networks is vital for uncovering illegal or unsafe activities, that can have serious environmental and regulatory consequences. Identifying anomalies in such networks presents a significant challenge due to the limited availability of labeled data and the subtle nature of illicit activities. Moreover, traditional anomaly detection methods relying solely on individual transaction data may overlook deeper, network-level irregularities that arise from complex interactions between entities, especially in the absence of labeled data. This study explores anomaly detection in a waste transport network using unsupervised learning, enhanced by limited supervision and enriched with network structure information. Initially, unsupervised models like Isolation Forest, K-Means, LOF, and Autoencoders were applied using statistical and graph-based features. These models detected outliers without prior labels. Later, information on a few confirmed anomalous users enabled weak supervision, guiding feature selection through statistical tests like Kolmogorov-Smirnov and Anderson-Darling. Results show that models trained on a reduced, graph-focused feature set improved anomaly detection, particularly under extreme class imbalance. Isolation Forest notably ranked known anomalies highly. Ego network visualizations supported these findings, demonstrating the value of integrating structural features and limited labels for identifying subtle, relational anomalies.

Abstract
Hyper-parameter optimization in machine learning models is critical for achieving peak performance. Over the past few years, numerous researchers have worked on this optimization challenge. They primarily focused on batch learning tasks where data distributions remain relatively unchanged. However, addressing the properties of data streams poses a substantial challenge. With the rapid evolution of technology, the demand for sophisticated techniques to handle dynamic data streams is becoming increasingly urgent. This paper introduces a novel adaptation of the Fish School Search (FSS) Algorithm for online hyper-parameter optimization, the FSS-SPT. The FSS-SPT is a solution designed explicitly for the dynamic context of data streams. One fundamental property of the FSS-SPT is that it can change between exploration and exploitation modes to cope with the concept drift and converge to reasonable solutions. Our experiments on different datasets provide compelling evidence of the superior performance of our proposed methodology, the FSS-SPT. It outperformed existing algorithms in two machine learning tasks, demonstrating its potential for practical application.

Abstract
One of the key aspects of Industry 4.0 is using intelligent systems to optimize manufacturing processes by improving productivity and reducing costs. These systems have greatly impacted in different areas, such as demand prediction and quality assessment. However, the prognostics and health management of industrial equipment is one of the areas with greater potential. This paper presents a comparative analysis of deep learning architectures applied to the prediction of the remaining useful life (RUL) on public real industrial datasets. The analysis includes some of the most commonly employed recurrent neural network variations and a novel approach based on a hybrid architecture using transformers. Moreover, we apply explainability techniques to provide comprehensive insights into the model's decision-making process. The contributions of the work are: (1) a novel transformer-based architecture for RUL prediction that outperforms traditional recurrent neural networks; (2) a detailed description of the design strategies used to construct the models on two under-explored datasets; (3) the use of explainability techniques to understand the feature importance and to explain the model's prediction and (4) making models built for reproducibility available to other researchers.

Abstract
Hierarchical document classification is essential for structuring large-scale textual corpora in domains such as digital libraries and academic repositories. While recent advances in large language models (LLMs) have opened new possibilities for text classification, their applicability to hierarchical settings under real-world constraints remains underexplored. This study investigates both generative and discriminative transformer-based models, evaluating their effectiveness across multiple inference strategies: zero-shot baseline, local fine-tuning, and a global approach using category-specific models. Experiments on two real-world hierarchical datasets provide a comprehensive comparison of classification accuracy, F1-macro scores, and inference times. The results highlight that, although generative LLMs can deliver competitive (yet variable) performance at higher levels of the hierarchy, their high inference costs hinder their use in time-sensitive applications. In contrast, fine-tuned discriminative models-particularly BERT-based architectures-consistently offer a more favorable trade-off between performance and efficiency.