Annals of Operations Research最新文献

This paper primarily focuses on grading barriers that hinder internet-of-things (IoTs) adoption, which eventually promotes sustainable supply chain execution. As countries globally plan to combat climate change, supply chain sustainability is substantial. Digital technology, such as IoT, supports sustainability within supply chains. Still, studies infer that the adoption could be more direct and involve barriers that must be graded for efficient implementation and planning. Previous barrier grading models (i) did not accept natural language-based ratings; (ii) subjective orientation of experts’ weights is not well explored; (iii) hybrid determination of attributes’ weights is lacking; and (iv) personalized grades for barriers are also unexplored. Motivated by these gaps, this article develops an integrated model by considering preferences in the natural language form via double hierarchy fuzzy data (DHFD). Later, the rank sum (RS) approach is presented for determining the weights of experts, and the RS-Cronbach factor is put forward for the hybrid weight calculation of attributes. An algorithm to grade barriers is proposed based on WISP formulation combined with the Copeland method. Finally, a case example from Coimbatore is presented to understand the framework’s usefulness, and sensitivity/comparison reveals the pros and cons of the framework.

In this golden age of artificial intelligence, transparency and responsible decision-making are paramount. While machine learning (ML) and operational research (OR) optimisations are fundamental aspects of AI, the benefits of explainable AI (XAI) for combinatorial optimisations remain underexplored. This study investigates the convergence of XAI and OR, emphasising the importance of transparency in combinatorial optimisations. Using the Knapsack problem as an example, we demonstrate that interpretable ML models can effectively solve combinatorial optimisation challenges and enhance transparency. Additionally, we illustrate the application of post-hoc XAI methods to OR optimisations solved with ML, providing transparent, human-friendly explanations. The key contributions of this work include proposing the application of the SAGE framework for transparent OR, demonstrating the integration of XAI with combinatorial optimisations, and offering practical guidelines for creating transparent explanations. These contributions can aid decision-makers in understanding, communicating, and trusting combinatorial optimisation solutions, paving the way for enhanced transparency in operational research across various sectors.

In recent years, the increasing interest in financial policies in more sustainable economics and the consequent growth of public awareness about environmental, social, and governance (ESG) companies’ issues have modified investors’ portfolio management through ESG considerations in investment decisions. Consequently, the classic Markowitz mean-variance solution based on expected returns and standard deviation has been modified to consider ESG firm characteristics. This study investigates how investors’ ESG preferences influence portfolio choices and decision-making processes. We employ a discrete-time homogeneous Markov model to analyze ESG rating migration patterns, simulate possible configurations of the efficient frontier in portfolios aligned with sustainable preferences, and optimize portfolio asset weights complying with ESG portfolio performance over a time period. The obtained results provide a means of assessing the impact of the investor’s propensity toward sustainability over time on portfolio profitability. This approach provides insights into how ESG considerations may reshape portfolio performance over time, fostering more informed and ethically guided financial decisions.

This editorial synthesizes the principal research trends and prospective directions emphasized in the special issue titled Emerging Trends in the Interplay between Analytics and Operations in MSMEs, published in Annals of Operations Research. The contributions underscore the transformative impact of analytics on Micro, Small, and Medium Enterprises (MSMEs), accentuating the integration of Industry 4.0 technologies, artificial intelligence (AI), machine learning, deep learning, blockchain, and big data analytics into operations management. Furthermore, the discussions illuminate emerging trends concerning the application of these technologies in MSMEs, presenting a future roadmap and directions regarding the interplay between analytics and operations. This also affirms a renewed focus on data analytics capabilities in enhancing operational efficiency, resilience, and sustainability within MSMEs. Prospective research directions encompass the development of transparent and responsible AI models, the addressing of implementation challenges related to business intelligence tools, and the fostering of dynamic capabilities to navigate the evolving digital landscape.

Financial distress prediction (FDP) is a critical task for financial institutions and is typically framed as a class imbalance learning problem. To address this challenge, this paper proposes two ensemble-based strategies: the homogeneous and heterogeneous approaches, which combine multiple data re-sampling algorithms to generate diverse re-balanced training sets for classifier construction. Experimental results on seven FDP datasets demonstrate that the heterogeneous approach, which integrates under-, over-, and hybrid sampling methods with their optimal imbalance ratio settings, achieves superior performance in terms of AUC, particularly when applied with the LightGBM and XGBoost classifiers. Regarding Type I error, the heterogeneous combinations consistently outperform the homogeneous and other baseline approaches across various classifiers. The generalizability of the proposed methods is further validated using 37 additional class-imbalanced datasets from different domains, where the heterogeneous approach again shows the most robust performance. These findings suggest that the proposed models can serve as effective decision support tools for financial institutions to enhance credit risk evaluation and lending strategies. From a policy perspective, adopting such predictive frameworks can improve financial stability by reducing exposure to high-risk loans and enabling more accurate early warning systems for economic distress.

We propose a novel analytical framework to study the equilibrium determination of ethical standards when a boycott movement (BM) that represents ethically concerned consumers pressures producers to scale back the production of objectionable products, at the expense of other, ethically indifferent, consumer groups. Focusing on monopolies, we find that under a fixed price regime monopolies—depending on the price—are either over or under appeasing the BM. If monopolies are free to set the price and boycotters substitute ethical violations with price reductions, then monopolies’ distortionary effect is twofold: (i) they are less likely to appease the BM compared to the social planner, and (ii) whenever they choose to appease, they over appease relative to the social optimum. Our results provide theoretical foundations for why producers in industries with abnormal customer willingness to pay such as luxury brands, are less likely to appease. The results also suggest that managers can use pricing mechanisms to exploit ethical demands of their customers. Conversely, governments should consider the welfare loss to the remaining consumer base caused by this exploitation.

With the occurrence of a public health crisis, the demand for healthcare services increases, which leads to an increase in the workload of hospitals. To overcome this predicament, hospitals should increase the number of their medical staff. Adding new medical staff, especially physicians, is a time-consuming process, and in such a situation, when the society is facing a shortage of physicians, it is almost impossible. Physician scheduling can be a practical solution to overcome this problem. Scheduling physicians without adding new physicians increases the workload of physicians, and this may affect their productivity and the service quality. To solve this problem, in addition to financial incentives, non-financial incentives such as increasing physicians' satisfaction should also be considered. Hence, by applying a novel mixed-integer linear programming (MILP) model, this study configures a decision support system for scheduling physicians by considering physicians' satisfaction during a public health crisis. The purpose of the proposed model is to maximize the fairness in the distribution of workload among physicians by considering their preferences. It should be noted that the satisfaction of physicians is considered using two indicators including equitable shifts distribution and physicians' preferences. The effectiveness of the proposed MILP model is examined using data from a hospital in Iran during the outbreak of the coronavirus disease (COVID-19). The investigated hospital consists of 15 regular departments that are served by 79 physicians. With the spread of COVID-19 pandemic, three departments are added to the existing departments to serve the COVID-19 patients. Finally, the proposed MILP model is implemented with and without considering physicians' preferences, and the effect of considering preferences on physician scheduling is shown.

The existing literature on the economic order quantity (EOQ) problem with backordering does not address the impact of batch shipments on backordering behavior in a business to customer (B2C) environment. This study develops inventory models for a retailer receiving batch shipments and managing inventory through backorders. In this scenario, a large quantity of items is received, some of which are found to be defective. To identify defective items, the retailer conducts a 100% inspection of the goods received. Once inspected, the saleable products are added to the warehouse inventory in batches, rather than individually. The retailer follows a policy of receiving equal-sized batches at regular time intervals, deciding on the number of batches, as well as the ordering and backordering quantities. The analysis explores two approaches for handling defective products, incorporating time-proportioning for the backordering cost and a penalty cost for each lost unit. The classical optimization technique is applied to determine the optimal policy. A numerical example demonstrates the theory, with results showing that partial recovery of customer loyalty and product repair are more profitable approaches.