Vera Miguéis

Abstract
In today's highly competitive fashion retail market, it is crucial to have accurate demand forecasting systems, namely for new products. Many experts have used machine learning techniques to forecast product sales. However, sales that do not happen due to lack of product availability are often ignored, resulting in censored demand and service levels that are lower than expected. Motivated by the relevance of this issue, we developed a two-stage approach to forecast the demand for new products in the fashion retail industry. In the first stage, we compared four methods of transforming historical sales into historical demand for products already commercialized. Three methods used sales-weighted averages to estimate demand on the days with stock-outs, while the fourth method employed an Expectation-Maximization (EM) algorithm to account for potential substitute products affected by stock-outs of preferred products. We then evaluated the performance of these methods and selected the most accurate one for calculating the primary demand for these historical products. In the second stage, we predicted the demand for the products of the following collection using Random Forest, Deep Neural Networks, and Support Vector Regression algorithms. In addition, we applied a model that consisted of weighting the demands previously calculated for the products of past collections that were most similar to the new products. We validated the proposed methodology using a European fashion retailer case study. The results revealed that the method using the Expectation-Maximization algorithm had the highest potential, followed by the Random Forest algorithm. We believe that this approach will lead to more assertive and better-aligned decisions in production management.

Abstract
Municipal solid waste (MSW) management has become a critical issue today, posing substantial economic, environmental, and social challenges. Identifying and analyzing dominant themes in this field is essential for advancing research and policies towards sustainable MSW management practices. This study aims to explore the key issues related to MSW management that have been addressed by both the scientific community and policymakers through funded projects. By doing so, the study seeks to guide the scientific community as a knowledge producer and the EU as a key funder. Two Latent Dirichlet Allocation (LDA) models were applied to analyze the themes from two corpora: one representing scientific literature and another focusing on EU-funded projects. Additionally, this analysis was complemented by a quantitative estimation of the similarity between the two corpora, providing a measure of alignment between the scientific community and policymakers. The results generally indicate that the two spheres are aligned and highlight the diversity of topics explored by the scientific community. Nevertheless, it is concluded that there are opportunities for further research on specific topics, such as leaching and the extraction of heavy metals. Additionally, the popularity of topics identified in European Union-funded projects has fluctuated considerably over time, focusing primarily on waste management rather than its prevention. In light of these findings, waste prevention emerges as a promising avenue for future EU-funded research initiatives.

Abstract
The retention of public transport users is widely acknowledged as a paramount challenge in the path towards the establishment of more sustainable cities and societies. In this setting, in which no contractual relationship with customers exists, an early and accurate prediction of whether a customer will remain with the company or leave, assumes great significance for businesses to develop effective retention strategies. This work focuses on this topic by identifying potential churners based on their past travel behavior. To achieve this, we developed a set of classification models using various machine learning techniques. These models were then employed as base learners within a stacking ensemble. All classifiers were developed with a profit-driven approach, optimizing for expected maximum profit. Finally, we calculated Shapley Additive Explanation values to enhance the interpretability of the proposed classifiers. The performance of the predictive models was evaluated using the data of taxi services recorded in a Portuguese city for 52 months. A broad range of predictors is proposed, including recency and frequency measures of taxi usage as well as others related to customers' satisfaction level. The predictive power of the models was also assessed for specific proportions of higher risk customers. All models have shown the capability to identify churners accurately. This study innovates in evaluating the one-to-one service provider company-customer relationship in the context of taxi industry. Retention actions to promote customers loyalty and enhance retention are also suggested. © 2025 The Author(s)

Abstract
Implementation of information and communication technologies (ICTs) in education is defined as the incorporation of ICTs into teaching and learning activities, both inside and outside the classroom. Despite widely studied, there is still no consensus on how it affects student performance. However, before evaluating this, it is crucial to identify which factors impact students' use of ICT for educational purposes. This understanding can help educational institutions to effectively implement ICT, potentially improving student results. Thus, adapting the conceptual framework proposed by Biagi and Loi (2013) and using the 2018 database of the Program for International Student Assessment (PISA) and a decision tree classification model developed based on CRISP-DM framework, we aim to determine which socio-demographic factors influence students' use of ICT for educational purposes. First, we categorized students according to their use of ICT for educational purposes in two situations: during lessons and outside lessons. Then, we developed a decision tree model to distinguish these categories and find patterns in each group. The model was able to accurately distinguish different levels of ICT adoption and demonstrate that ICT use for entertainment and ICT access at school and at home are among the most influential variables to predict ICT use for educational purposes. Moreover, the model showed that variables related to teaching best practices of Internet utilization at school are not significant predictors of such use. Some results were found to be country-specific, leading to the recommendation that each country adapts the measures to improve ICT use according to its context.

Abstract
Data-driven models have been recognized as powerful tools to support Structural Health Monitoring (SHM). This paper contributes to the literature by exploring two data-driven approaches to detect damage through changes in a set of variables that assess the condition of the structure, and accommodates the challenge that may arise due to the influence of environmental and operational variabilities. This influence is reflected in the response of the structure and can reduce the probability of detecting damage in a structure or increase the probability of signaling false positives. This paper conducts a comparative study between a machine learning detection approach (supported by linear regression, random forest, support vector machine, and neural networks) and a cointegration approach, with the aim of detecting damage as early as possible. This study also contributes to the literature by evaluating the merits of the damage detection methods using real data collected from a small-scale structure. The structure is analyzed in a reference state and a perturbed state in which damage is emulated. The results show that both approaches are able to detect damage within the first 24 h, without ever signaling false positives. The cointegration based approach can notably detect damage after 10 h and 15 minutes, while the machine learning approach takes 20 h 30 m to detect damage.