Operations Research Perspectives最新文献

The educational system determines one of the significant strengths of an advanced society. A country with a lack of culture is less competitive due to the inequality suffered by its people. Institutions and organizations are putting their efforts into tackling that problem. Nevertheless, it is not an easy task to ascertain why their students have failed or what are the conditions that affect such situations. In this work, an intelligent system is proposed to predict academic failure by using student information stored by the Industrial University of Santander (Colombia). The prediction model is powered by the XGBoost algorithm, where a TOPSIS-based feature extraction and ADASYN oversampling have been conducted. Hyperparameters of the classifier were tuned by a cross-validated grid-search algorithm. We have compared our results with other decision-tree classifiers and displayed the feature importance of our intelligent system as an explainability phase. In conclusion, our intelligent system has shown a superior performance of our prediction model and has indicated to us that economic, health and social factors are decisive for the academic performance of the students.

We present a two-stage scheduling approach including proactive and reactive scheduling to solve the ground resource scheduling problem with uncertain arrival time. In the first stage, an integer programming model is constructed to minimize the delay and transfer costs. After solving this model, we obtain a baseline scheduling plan that considers the service arrival time uncertainty. In the second stage, the feasibility of the subsequent benchmark plan is evaluated based on the current state of the services and resources. The reactive scheduling model is enabled when trigger conditions are met. Moreover, an improved adaptive large neighborhood search is designed to solve the proactive scheduling model effectively. Real data from an international airport in South China is used as a test case to compare different scheduling strategies. The results show that it is difficult to handle the uncertainty of the problem with the benchmark plan that simply considered buffer time. Compared with rolling time-domain scheduling, the average transfer cost of the scheduling strategy proposed in this paper increased slightly, but the average service delay cost can be reduced significantly. Algorithm-wise, instances of different scales are designed to verify the effectiveness of the improved adaptive large neighborhood search algorithm. The efficiency of the algorithm scheme is better than that of the Gurobi solver scheme in medium to large-scale problems. Therefore, the forward and reactive strategies can better handle the uncertainty of airport ground protection services as they can simultaneously guide the allocation and utilization of airport ground protection resources.

Regulators’ increasingly stringent carbon rules to protect the environment are encouraging practitioners to modify their operational activities that are accountable for releasing emissions into the atmosphere. Thereby, practitioners dealing with product inventory planning are seeking proper management strategies not only to increase profits but also to reduce released carbons from operations. In addition, increasing uncertainty in supply operations has motivated suppliers to impose prepayment mechanisms in recent decades. This study examines the best prepayment installment policy for a practitioner for the first time, where the consumption behavior of consumers changes as a result of the combined effects of unit selling price and storage time. Moreover, to make the present inventory planning more realistic, the unit holding cost function is adopted as a power function of the inventory unit's storage period. The goal of this study is to provide the best combined installment for advance payment, price, and replenishment strategies for a practitioner under cap-and-price, cap-and-trade, and carbon tax environmental guidelines by ensuring maximum profit. For this purpose, an algorithm is created by combining all derived theoretical results from the analytical study, whereas the efficacy of the algorithm is assessed through the examination of five illustrative numerical instances. A plethora of noteworthy management insights for the practitioner are obtained by investigating the dynamic shifts in optimal strategies resulting from fluctuations in system parameters. The results reveal that if the demand is low in the nascent phases of the business cycle, then the prudent approach for the practitioner entails procuring a comparatively smaller lot-size using a modest number of payment frequencies and then setting a relatively small unit selling price to increase profits.

This paper is concerned with prescriptive price optimization, which integrates machine learning models into price optimization to maximize future revenues or profits of multiple items. The prescriptive price optimization requires accurate demand forecasting models because the prediction accuracy of these models has a direct impact on price optimization aimed at increasing revenues and profits. The goal of this paper is to establish a novel framework of prescriptive price optimization using optimal regression trees, which can achieve high prediction accuracy without losing interpretability by means of mixed-integer optimization (MIO) techniques. We use the optimal regression trees for demand forecasting and then formulate the associated price optimization problem as a mixed-integer linear optimization (MILO) problem. We also develop a scalable heuristic algorithm based on the randomized coordinate ascent for efficient price optimization. Simulation results demonstrate the effectiveness of our method for price optimization and the computational efficiency of the heuristic algorithm.

This study investigates a green supply chain consisting of a capital-constrained developer who sells a product via a platform. The parties interact via an agency contract, in which the platform charges a fixed proportion of the revenue gained from each sold unit and the developer receives the remaining sum. Since the development process is relatively protracted, at the early stages of this process, the commission rate to be charged by the platform is random from the developer’s perspective. Upon receiving information about the amount of capital the developer has committed to investing in greenness from his own resources, an external investor offers the developer a loan at a certain interest rate (to further enhance the developer’s investment in greenness), based on which the developer sets the product’s greenness level and selling price. The study provides a game-theoretic analysis of this model and compares its equilibrium solution with the optimal solution of a fully self-financing developer. The innovative feature of the study lies in its comparison between the case of a developer who might not be able to repay the loan, because his revenue from selling the product might be lower than the amount he is required to repay the investor (the loan plus interest), and the case in which it is certain that the developer will be able to repay any debt to the investor. Our study shows that, in the case where the investor takes on the financing risk, the customers benefit from a higher greenness level (albeit at a higher price), resulting in greater demand for the product.

In distribution systems such as airlines and express package delivery, the use of hub-and-spoke networks is common, and flow consolidation at hub facilities is essential for cost reduction. While a constant discount factor is typically used to model cost reduction in interhub links, this paper explores an extension of the incomplete hub location problem with modular capacity that enables direct connections between non-hub nodes. The modified approach, called MHLPDC, aims to locate a set of hub facilities, connect each non-hub node to a hub, and activate hub facility links, access arc links, and direct links between non-hub nodes to minimize network costs. The MHLPDC integrates link activation decisions into the decision-making process and utilizes modular arc costs to model the flow dependence of transportation costs in all arcs. To solve the problem, the paper presents a mixed-integer mathematical programming formulation and heuristic algorithm based on a greedy randomized adaptive search and variable neighborhood search approach. The proposed algorithm produces high-quality solutions, as demonstrated through computational experiments on benchmark instances with up to 40 nodes. Furthermore, a sensitivity analysis of the optimal network structure indicates that increasing the discount factor, by varying hub and access arc capacities as well as the associated variable costs, results in fewer hubs being established and more direct shipments between non-hub nodes being permitted.

After a pandemic, all countries experience a shortage in vaccine supply due to limited vaccine stocks and production capacity globally. One particular problem is that it is hard to predict demands for vaccines during the global crisis. On the other hand, vaccines are usually made and packaged in different places, raising logistical issues and concerns that can further delay distribution. In this paper, we propose an optimization formulation model to link infectious disease dynamics and supply chain networks considering a one-to-one relationship between demand and supply for vaccines. We focus on designing a vaccine coordination system using government subsidy that considers the equilibrium behaviors of manufacturers under an actual demand for the vaccine. This study evaluates vaccine manufacturers and government behaviors that help the vaccine market to reach the socially optimal. Different decisions, such as vaccine demands and vaccine production and distribution are investigated. A study of the monkeypox pandemic in the U.S. is performed to validate our model and its results. The obtained results from testing the proposed system problem revealed that the vaccine coverage increased by up to 35%, while the unmet demand reduced by up to 60%, in comparison to when vaccine manufacturers act individually.

This paper studies the static economic optimization problem of a system with a single aggregator and multiple prosumers in a Real-Time Balancing Market (RTBM). The aggregator, as the agent responsible for portfolio balancing, needs to minimize the cost for imbalance satisfaction in real-time by proposing a set of optimal personalized prices to the prosumers. On the other hand, the prosumers, as price taker and self-interested agents, want to maximize their profit by changing their supplies or demands and providing flexibility based on the proposed personalized prices. We model this problem as a bilevel optimization problem. We first show that the optimal solution of this bilevel optimization problem can be found by solving an equivalent convex problem. In contrast to the state-of-the-art Mixed-Integer Programming (MIP)-based approach to solve bilevel problems, this convex equivalent has very low computation time and is appropriate for real-time applications. Next, we compare the optimal solutions of the proposed personalized scheme and a uniform pricing scheme. We prove that, under the personalized pricing scheme, more prosumers contribute to the RTBM and the aggregator’s cost is less. Finally, we verify the analytical results of this work by means of numerical case studies and simulations.

To remain competitive, companies must decide on new, desirable products. This can be achieved by integrating insights how customers use a product into the process of deciding on a new product. Currently, this process is primarily based on market research that can only reveal the intention of consumers. Through the digitization of products, companies have access to large amounts of customer data that allow the application of data analytics methods. We provide a taxonomy of artificial intelligence, machine learning and data analysis, so that the notion of data analytics can be defined. Thus, the terms customer usage data, as well as a generic, five-stage product decision process (PDP) are defined and differentiated from consumer data and the product development process. Eventually, we show which data analytics methods on customer usage data can be used in order to tackle current challenges within the PDP. We incorporate the results of our structured literature review by connecting selected examples to our concept of the PDP. Our insights help to apply the proper data analytics methods in the PDP and thereby address the interplay between product decision and product development. Finally, future research directions for data analytics methods on customer usage data are put forward.

Broiler chickens are specially raised for meat production and their supply chain is composed of breeders, hatcheries, feed mills, farms, slaughterhouses, wholesalers, and retailers. The coordination between supply chain players has great potential to streamline production and increase competitiveness in the market. A critical element in the decision-making process of this agri-system is the weight gain of broiler chickens. Variability in chicken growth patterns can affect production plans in practice. The most efficient weight estimation models require sensors in real-time, which are not available in many companies. Thus, some small farms require a simpler approach to adjust production planning based on the uncertainty of chickens’ weight while they transition to new technologies. This research proposes an optimization-based methodology for the integration of farms and slaughterhouses to plan production under chicken growth uncertainty. The methodology includes two models: (i) a two-stage stochastic model that supports lot-sizing and inventory management decisions while considering scenarios of chicken growth uncertainty; and (ii) a mixed-integer linear programming model that supports lot allocation. We present the results of implementing the methodology in a poultry company in Santa Marta (Colombia), where we improved costs by 8.6% while meeting tactical, biological, and biosecurity constraints.