Abstract
This special issue showcases state-of-the-art research at the intersection of analytics and retail operations. As the retail landscape becomes increasingly complex – driven by omnichannel strategies, evolving customer expectations, and a surge in data availability – analytics has emerged as a critical enabler of operational efficiency, customer experience, responsiveness, and sustainability and ethics. Collectively, these contributions demonstrate how advanced analytics can support retailers in navigating uncertainty, personalizing services, and scaling up innovation across formats and channels. The articles featured in this issue address a diverse set of decision domains, including warehousing, inventory and assortment planning, and distribution and last-mile delivery. Methodologically, they span descriptive, prescriptive, and hybrid approaches, leveraging tools such as machine learning, stochastic modeling, and dynamic optimization. By grounding models in real-world data and focusing on practical implementation, the issue provides actionable insights for both scholars and practitioners. It also highlights emerging opportunities for future research on behavioral integration, human-machine collaboration, and the ethical dimensions of retail analytics. © 2025 Elsevier B.V.

Abstract
Subject-independent seizure detection algorithms are typically grounded in scalp electroencephalogram (EEG) databases, due to standardized channels and locations of EEG electrodes. Intracranial EEG (iEEG) has the characteristics of low noise and high temporal resolution compared with scalp EEG. However, it is still a big challenge for seizure detection using iEEG, because of the inconsistent number and locations of implanted electrodes in different patients, which results in a lack of unified algorithms. This study introduces an innovative approach for subject-independent seizure detection using iEEG, combining channel-wise mixup, transformer networks, and multi-task learning. Channel-wise mixup enhances data utilization by effectively leveraging information from different subjects, while multi-task learning improves the generalization of the model by concurrently optimizing both the seizure detection and the subject recognition tasks. 2983 files from two well-known epilepsy databases, i.e. SWEC-ETHZ and HUP were used in our study and the result showed that our approach surpasses currently existing methods. In terms of accuracy and generalization of seizure detection, our method achieved an area under the receiver operating characteristic curve (AUC) of 0.97 and 0.95 on the two databases respectively, which are significantly higher than the result of the currently existing methods. This study proposed anew method with great potential for surgery planning of epilepsy patients.

Abstract
Energy communities (EC) and collective self-consumption (CSC) systems can make a significant contribution to reducing dependence on fossil fuels and energy costs. They create mechanisms for the active participation of end-consumers in the energy system by becoming self-producers of renewable electricity and adapting their energy behavior to the needs of the system. CSC also alleviates energy poverty by reducing the energy costs of vulnerable members. The CSC is still in its early stages, and regulation is being developed in several countries along with pilot projects to test different rules and incentives. This chapter discusses the most relevant common definitions of CSC and EC so far, as well as the main challenges in relation to energy sharing rules and the management of EC and CSC. © 2025 Elsevier B.V., All rights reserved.

Abstract
In online grocery retail, out-of-stocks can cause order fulfillment failures. Store-based fulfillment models have heightened this challenge. Here, online customers often receive orders not fulfilled as expected, with products being substituted, partially fulfilled, or reimbursed. When order fulfillment fails, the customer may change future ordering behavior by delaying the next order or by spending less in the online channel. Using data from the online operation of a leading omnichannel grocery retailer, we evaluate the magnitude of impact on the next order when the prior one is not fulfilled as expected. We also explore the role of retailer efforts in mitigating this impact. We find that failures significantly delay the time to the next order by 7.22% on average, with delays becoming more pronounced for non-perishable products. Spending reductions are especially evident when promoted items fail to ship. Mitigation efforts, substitutions in particular, often exacerbate delays and compound the dissatisfaction. Although substitutions help recover lost sales, they negatively impact future customer behavior. This suggests that selective stockout prevention, coupled with improved substitution practices, should be prioritized to optimize economic and customer outcomes.

Abstract
Free-floating sharedmicromobility services have been present in cities all around the world, however little is still known about the interaction between shared e-bikes and e-scooters. In the last few years shared e-scooters have experienced rapid growth worldwide, which, in some cities, jeopardizes the usage of shared e-bike services. Thus, this research work aims to explore if free-floating shared e-bikes can disrupt the usage of established e-scooter services. Acase study in the city of Braga, north of Portugal, is developed from September of 2022 until May of 2023 in order to allow the comparison and contrast of the trips made by each micromobility mode, travel time, main origin and destinations of trips, as well as trip characteristics (e.g., vehicle rotation, the total number of trips per micromobility mode, total distance traveled). Results showthat shared e-bikes and e-scooters are only used within city boundaries, and most of the trips originated in the parish where population density is higher. In Braga, riders prefer e-scooters when using a shared micro vehicle, since more than 98% of the trips made in the period studied weremade by this mode. Also, shared e-scooters traveled more than 260,000 km in these nine months, while only 2,400 km were traveled in e-bikes. In short, Braga has experienced a rapid establishment of shared e-scooters instead of shared e-bikes, it can be due to the fact that trips on e-scooters are seen to be fun, pleasant, and quicker by riders.

Abstract