In recent years, the integration of artificial intelligence (AI) into logistics optimization has gained significant attention, particularly concerning sustainability criteria. This article provides an overview of the diverse AI models and algorithms employed in logistics optimization, with a focus on sustainable practices. The discussion covers several techniques, including generative models, machine learning methods, metaheuristic algorithms, and their synergistic combinations with traditional optimization and simulation methods. By employing AI capabilities, logistics stakeholders can enhance decision-making processes, optimize resource utilization, and minimize environmental impacts. Moreover, this paper identifies and analyzes prominent challenges within sustainable logistics, such as reducing carbon emissions, minimizing waste generation, and optimizing transportation routes while considering ecological factors. Furthermore, the paper explores emerging trends in AI-driven logistics optimization, such as the integration of real-time data analytics, blockchain technology, and autonomous systems, which hold immense potential for enhancing efficiency and sustainability. Finally, the paper outlines future research directions, emphasizing the need for further exploration of hybrid AI approaches, robust optimization frameworks, and scalable solutions that accommodate dynamic and uncertain logistics environments.

This paper explores how the combination of artificial intelligence, simulation, and e-collaborative (AISEC) tools can support accessibility in analytics courses within higher education. In the era of online and blended learning, addressing the diverse needs of students with varying linguistic backgrounds and analytical proficiencies poses a significant challenge. This paper discusses how the combination of AISEC tools can contribute to mitigating barriers to accessibility for students undertaking analytics courses. Through a comprehensive review of existing literature and empirical insights from practical implementations, this paper shows the synergistic benefits of using AISEC tools for facilitating interactive engagement in analytics courses. Furthermore, the manuscript outlines practical strategies and best practices derived from real-world experiences carried out in different universities in Spain, Ireland, and Portugal.

This paper proposes a novel methodology, based on machine learning and statistical models, for predicting hurricane-related losses to specific assets. Our approach uses three critical storm parameters typically tracked by meteorological agencies: maximum wind speed, minimum sea level pressure, and radius of maximum wind. The system categorizes potential damage events into three insurance-relevant classes: non-payable, partially payable, and fully payable. Three triggers for final payouts were designed: hybrid framework, standalone regression, and standalone non-linear regression. The hybrid framework combines two classification models and a non-linear regression model in an ensemble specifically designed to minimize the absolute differences between predicted and actual payouts (Total Absolute Error or TAE), addressing highly imbalanced and partially compensable events. Although this complex approach may not be suitable for all current contracts due to limited interpretability, it provides an approximate lower bound for the minimization of the absolute error. The standalone non-linear regression model is structurally simpler, yet it likewise offers limited transparency. This hybrid framework is not intended for direct deployment in parametric insurance contracts, but rather serves as a benchmarking and research tool to quantify the achievable reduction in basis risk under highly imbalanced conditions. The standalone linear regression provides an interpretable linear regression model optimized for feature selection and interaction terms, enabling direct deployment in parametric insurance contracts while maintaining transparency. These three approaches allow analysis of the trade-off between model complexity, predictive performance, and interpretability. The three approaches are compared using comprehensive hurricane simulation data from an industry-standard catastrophe model. The methodology is particularly valuable for parametric insurance applications, where rapid assessment and claims settlement are essential.

This paper presents a reinforcement learning (RL) approach for solving the team orienteering problem under both deterministic and dynamic travel time conditions. The proposed method builds on the transformer architecture and is trained to construct routes that adapt to real-time variations, such as traffic and environmental changes. A key contribution of this work is the model’s ability to generalize across problem instances with varying numbers of nodes and vehicles, eliminating the need for retraining when problem size changes. To assess performance, a comprehensive set of experiments involving 27,000 synthetic instances is conducted, comparing the RL model with a variable neighborhood search metaheuristic. The results indicate that the RL model achieves competitive solution quality while requiring significantly less computational time. Moreover, the RL approach consistently produces feasible solutions across all dynamic instances, demonstrating strong robustness in meeting time constraints. These findings suggest that learning-based methods can offer efficient, scalable, and adaptable solutions for routing problems in dynamic and uncertain environments.

This paper addresses a dynamic multi-period pricing problem that incorporates time-varying contextual information and inventory constraints. Sales are modeled as a function of both price and a multidimensional context vector, which may include factors such as customer location, income, loyalty, competitor prices, and promotional activity. This formulation captures complex market dynamics over a finite selling horizon. The problem is formulated as a quadratic programming model, and two alternative solution approaches are proposed. The first uses a multivariate regression model to approximate the sales function linearly, allowing an exact quadratic programming solution that serves as a benchmark. The second is a ‘learnheuristic’ algorithm that combines a nonlinear sales learning model with metaheuristic optimization to generate high-quality pricing strategies under realistic operational constraints. Computational experiments demonstrate the effectiveness of the proposed learnheuristic approach.