Computers & Operations Research最新文献_第9页

Data-driven robust flexible personnel scheduling

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-12-06 DOI: 10.1016/j.cor.2024.106935

Zilu Wang , Zhixing Luo , Huaxiao Shen

Personnel scheduling in various industries often faces challenges due to unpredictable workloads. This paper focuses on the general flexible personnel scheduling problem at the operational level, which is characterized by uncertain demand and limited knowledge of the true distribution of this demand. To address this issue, we propose a distributionally robust model that utilizes the Wasserstein ambiguity set. This model is designed to maintain service levels across the worst-case distribution scenarios of random demand. In addition, we introduce a robust satisficing model that is oriented towards specific targets, offering practical applicability in real-world situations. Both models leverage empirical distributions derived from historical data, enabling the generation of robust personnel schedules that are responsive to uncertain demand, even when data availability is limited. We demonstrate that these robust models can be transformed into tractable counterparts. Moreover, we develop an exact depth-first search algorithm for identifying feasible daily schedules. Through a comprehensive case study and experiments using real-world data, we showcase the effectiveness and advantages of our proposed models and algorithms. The robustness of our models is thoroughly evaluated, providing valuable management insights and demonstrating their ability to tackle scheduling challenges in uncertain environments.

{"title":"Data-driven robust flexible personnel scheduling","authors":"Zilu Wang , Zhixing Luo , Huaxiao Shen","doi":"10.1016/j.cor.2024.106935","DOIUrl":"10.1016/j.cor.2024.106935","url":null,"abstract":"<div><div>Personnel scheduling in various industries often faces challenges due to unpredictable workloads. This paper focuses on the general flexible personnel scheduling problem at the operational level, which is characterized by uncertain demand and limited knowledge of the true distribution of this demand. To address this issue, we propose a distributionally robust model that utilizes the Wasserstein ambiguity set. This model is designed to maintain service levels across the worst-case distribution scenarios of random demand. In addition, we introduce a robust satisficing model that is oriented towards specific targets, offering practical applicability in real-world situations. Both models leverage empirical distributions derived from historical data, enabling the generation of robust personnel schedules that are responsive to uncertain demand, even when data availability is limited. We demonstrate that these robust models can be transformed into tractable counterparts. Moreover, we develop an exact depth-first search algorithm for identifying feasible daily schedules. Through a comprehensive case study and experiments using real-world data, we showcase the effectiveness and advantages of our proposed models and algorithms. The robustness of our models is thoroughly evaluated, providing valuable management insights and demonstrating their ability to tackle scheduling challenges in uncertain environments.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"176 ","pages":"Article 106935"},"PeriodicalIF":4.1,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Equity-driven facility location: A two-stage robust optimization approach

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-30 DOI: 10.1016/j.cor.2024.106920

Amin Ahmadi Digehsara , Menglei Ji , Amir Ardestani-Jaafari , Hoda Bidkhori

This paper explores the computational challenge of incorporating equity in p-median facility location models under uncertain demand and discusses how two-stage robust programming can be employed to address the challenge. Our research evaluates various equity measures appropriate for facility location modeling and proposes a novel approach to reformulating the problem into a two-stage robust optimization framework, enhancing computational efficiency caused by incorporating equity and uncertainty into these models. We provide two solution algorithms: an exact and an inexact column-and-constraint generation (C&CG) method. Our findings suggest that although the exact C&CG method generally outperforms the inexact approach, both methods perform well when the number of variables is small, with the inexact C&CG demonstrating a slight advantage in computational time. We further conduct a detailed evaluation of the tractability of our reformulated model and the effectiveness of various equity measures through a real-world case study of Metro Vancouver.

引用次数: 0

Graph neural networks for job shop scheduling problems: A survey

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-29 DOI: 10.1016/j.cor.2024.106914

Igor G. Smit , Jianan Zhou , Robbert Reijnen , Yaoxin Wu , Jian Chen , Cong Zhang , Zaharah Bukhsh , Yingqian Zhang , Wim Nuijten

Job shop scheduling problems (JSSPs) represent a critical and challenging class of combinatorial optimization problems. Recent years have witnessed a rapid increase in the application of graph neural networks (GNNs) to solve JSSPs, albeit lacking a systematic survey of the relevant literature. This paper aims to thoroughly review prevailing GNN methods for different types of JSSPs and the closely related flow-shop scheduling problems (FSPs), especially those leveraging deep reinforcement learning (DRL). We begin by presenting the graph representations of various JSSPs, followed by an introduction to the most commonly used GNN architectures. We then review current GNN-based methods for each problem type, highlighting key technical elements such as graph representations, GNN architectures, GNN tasks, and training algorithms. Finally, we summarize and analyze the advantages and limitations of GNNs in solving JSSPs and provide potential future research opportunities. We hope this survey can motivate and inspire innovative approaches for more powerful GNN-based approaches in tackling JSSPs and other scheduling problems.

{"title":"Graph neural networks for job shop scheduling problems: A survey","authors":"Igor G. Smit , Jianan Zhou , Robbert Reijnen , Yaoxin Wu , Jian Chen , Cong Zhang , Zaharah Bukhsh , Yingqian Zhang , Wim Nuijten","doi":"10.1016/j.cor.2024.106914","DOIUrl":"10.1016/j.cor.2024.106914","url":null,"abstract":"<div><div>Job shop scheduling problems (JSSPs) represent a critical and challenging class of combinatorial optimization problems. Recent years have witnessed a rapid increase in the application of graph neural networks (GNNs) to solve JSSPs, albeit lacking a systematic survey of the relevant literature. This paper aims to thoroughly review prevailing GNN methods for different types of JSSPs and the closely related flow-shop scheduling problems (FSPs), especially those leveraging deep reinforcement learning (DRL). We begin by presenting the graph representations of various JSSPs, followed by an introduction to the most commonly used GNN architectures. We then review current GNN-based methods for each problem type, highlighting key technical elements such as graph representations, GNN architectures, GNN tasks, and training algorithms. Finally, we summarize and analyze the advantages and limitations of GNNs in solving JSSPs and provide potential future research opportunities. We hope this survey can motivate and inspire innovative approaches for more powerful GNN-based approaches in tackling JSSPs and other scheduling problems.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"176 ","pages":"Article 106914"},"PeriodicalIF":4.1,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A literature review of reinforcement learning methods applied to job-shop scheduling problems 强化学习方法应用于作业车间调度问题的文献综述

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-27 DOI: 10.1016/j.cor.2024.106929

Xiehui Zhang, Guang-Yu Zhu

The job-shop scheduling problem (JSP) is one of the most famous production scheduling problems, and it is an NP-hard problem. Reinforcement learning (RL), a machine learning method capable of feedback-based learning, holds great potential for solving shop scheduling problems. In this paper, the literature on applying RL to solve JSPs is taken as the review object and analyzed in terms of RL methods, the number of agents, and the agent upgrade strategy. We discuss three major issues faced by RL methods for solving JSPs: the curse of dimensionality, the generalizability and the training time. The interconnectedness of the three main issues is revealed and the main factors affecting them are identified. By discussing the current solutions to the above issues as well as other challenges that exist, suggestions for solving these problems are given, and future research trends are proposed.

车间作业调度问题（JSP）是最著名的生产调度问题之一，属于np困难问题。强化学习（RL）是一种基于反馈学习的机器学习方法，在解决车间调度问题方面具有很大的潜力。本文以应用强化学习解决jsp的文献为综述对象，从强化学习方法、agent数量、agent升级策略等方面进行分析。我们讨论了RL方法在解决jsp时面临的三个主要问题：维度的诅咒、泛化性和训练时间。揭示了三个主要问题的相互联系，并确定了影响它们的主要因素。通过讨论目前解决上述问题的方法以及存在的其他挑战，提出了解决这些问题的建议，并提出了未来的研究趋势。

引用次数: 0

An accelerated Benders decomposition method for distributionally robust sustainable medical waste location and transportation problem 分布式稳健可持续医疗废物定位与运输问题的加速Benders分解方法

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-26 DOI: 10.1016/j.cor.2024.106895

Zihan Quan , Yankui Liu , Aixia Chen

This study addresses the sustainable medical waste location and transportation (SMWLT) problem from the viewpoint of social risk, environmental impact, and economic performance, where model uncertainty includes risk and transportation costs. In practice, it is usually hard to obtain the exact probability distribution of uncertain parameters. To address this challenge, this study first constructs an ambiguity set to model the partial distribution information of uncertain parameters. Based on the constructed ambiguity set, this study develops a new multi-objective distributionally robust chance-constrained (DRCC) model for the SMWLT problem. Subsequently, this study adopts the robust counterpart (RC) approximation method to reformulate the proposed DRCC model as a computationally tractable mixed-integer linear programming (MILP) model. Furthermore, an accelerated Benders decomposition (BD) enhanced by valid inequalities is designed to solve the resulting MILP model, which significantly improves the solution efficiency compared with the classical BD algorithm and CPLEX solver. Finally, a practical case in Chongqing, China, is addressed to illustrate the effectiveness of our DRCC model and the accelerated BD solution method.

本研究从社会风险、环境影响和经济效益的角度探讨医疗废弃物永续安置与运输问题，其中模型不确定性包括风险和运输成本。在实际应用中，通常很难得到不确定参数的精确概率分布。为了解决这一挑战，本研究首先构建了一个模糊集来模拟不确定参数的部分分布信息。基于构建的模糊集，本文提出了一种新的SMWLT问题的多目标分布鲁棒机会约束（DRCC）模型。随后，本文采用鲁棒对应（RC）近似方法将所提出的DRCC模型重新表述为可计算的混合整数线性规划（MILP）模型。在此基础上，设计了一种基于有效不等式的加速Benders分解（Benders decomposition， BD）来求解MILP模型，与传统的Benders分解算法和CPLEX求解器相比，显著提高了求解效率。最后，以中国重庆的一个实际案例为例，说明了我们的DRCC模型和加速BD解决方法的有效性。

{"title":"An accelerated Benders decomposition method for distributionally robust sustainable medical waste location and transportation problem","authors":"Zihan Quan , Yankui Liu , Aixia Chen","doi":"10.1016/j.cor.2024.106895","DOIUrl":"10.1016/j.cor.2024.106895","url":null,"abstract":"<div><div>This study addresses the sustainable medical waste location and transportation (SMWLT) problem from the viewpoint of social risk, environmental impact, and economic performance, where model uncertainty includes risk and transportation costs. In practice, it is usually hard to obtain the exact probability distribution of uncertain parameters. To address this challenge, this study first constructs an ambiguity set to model the partial distribution information of uncertain parameters. Based on the constructed ambiguity set, this study develops a new multi-objective distributionally robust chance-constrained (DRCC) model for the SMWLT problem. Subsequently, this study adopts the robust counterpart (RC) approximation method to reformulate the proposed DRCC model as a computationally tractable mixed-integer linear programming (MILP) model. Furthermore, an accelerated Benders decomposition (BD) enhanced by valid inequalities is designed to solve the resulting MILP model, which significantly improves the solution efficiency compared with the classical BD algorithm and CPLEX solver. Finally, a practical case in Chongqing, China, is addressed to illustrate the effectiveness of our DRCC model and the accelerated BD solution method.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"175 ","pages":"Article 106895"},"PeriodicalIF":4.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A VNS method for the conditional p-next center problem 条件p-下一中心问题的VNS方法

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-26 DOI: 10.1016/j.cor.2024.106916

Jelena Tasić, Zorica Dražić, Zorica Stanimirović

This paper considers the conditional

p

-next center problem (CPNCP) and proposes a metaheuristic method as a solution approach. The

p

-next center problem (PNCP) is an extension of the classical

p

-center problem that captures real-life situations when centers suddenly fail due to an accident or some other problem. When the center failure happens, the customers allocated to the closed center are redirected to the center closest to the closed one, called the backup center. On the other hand, when a service network expands, some of the existing centers are usually retained and a number of new centers are opened. The conditional

p

-next center problem involves both of these two aspects that arise in practice and, to the best of our knowledge, has not been considered in the literature so far. Since the CPNCP is NP-hard, a metaheuristic algorithm based on the Variable Neighborhood Search is developed. The proposed VNS includes an efficient implementation of the Fast Interchange heuristic which enables the VNS to tackle with real-life problem dimensions. The exhaustive computational experiments were performed on the modified PNCP test instances from the literature with up to 900 nodes. The obtained results are compared with the results of the exact solver CPLEX. It is shown that the proposed VNS reaches optimal solutions or improves the feasible ones provided by CPLEX in a significantly shorter CPU time. The VNS also quickly returns its best solutions when CPLEX failed to provide a feasible one. In order to investigate the effects of two different approaches in service network planning, the VNS solutions of the CPNCP are compared with the optimal or best-known solutions of the

p

-next center problem. In addition, the conducted computational study includes direct comparisons of the results obtained when the proposed SVNS is applied to PNCP (by setting the number of existing centers to 0) with the results of recent solution methods proposed for the PNCP.

本文考虑了条件p-下一中心问题（CPNCP），提出了一种元启发式求解方法。下一个p中心问题（PNCP）是经典p中心问题的扩展，它捕获了由于事故或其他问题导致中心突然失效的现实情况。当中心发生故障时，分配到关闭中心的客户被重定向到离关闭中心最近的中心，称为备份中心。另一方面，当一个服务网络扩大时，通常会保留一些现有的中心，并开设一些新的中心。条件p-下一中心问题涉及到实践中出现的这两个方面，据我们所知，迄今为止还没有在文献中得到考虑。针对CPNCP的np困难特性，提出了一种基于变邻域搜索的元启发式算法。提出的VNS包括快速交换启发式的有效实现，使VNS能够处理现实生活中的问题维度。在文献中改进的PNCP测试实例上进行了详尽的计算实验，其节点数高达900个。所得结果与精确求解器CPLEX的结果进行了比较。结果表明，所提出的VNS在较短的CPU时间内达到了最优解或改进了CPLEX提供的可行解。当CPLEX无法提供可行的解决方案时，VNS也会迅速返回最佳解决方案。为了研究两种不同方法在业务网络规划中的效果，将CPNCP的VNS解与p-next中心问题的最优解或最知名解进行了比较。此外，所进行的计算研究包括将所提出的SVNS应用于PNCP（通过将现有中心数量设置为0）时获得的结果与最近提出的PNCP解决方法的结果进行直接比较。

{"title":"A VNS method for the conditional p-next center problem","authors":"Jelena Tasić, Zorica Dražić, Zorica Stanimirović","doi":"10.1016/j.cor.2024.106916","DOIUrl":"10.1016/j.cor.2024.106916","url":null,"abstract":"<div><div>This paper considers the conditional <span><math><mi>p</mi></math></span>-next center problem (CPNCP) and proposes a metaheuristic method as a solution approach. The <span><math><mi>p</mi></math></span>-next center problem (PNCP) is an extension of the classical <span><math><mi>p</mi></math></span>-center problem that captures real-life situations when centers suddenly fail due to an accident or some other problem. When the center failure happens, the customers allocated to the closed center are redirected to the center closest to the closed one, called the backup center. On the other hand, when a service network expands, some of the existing centers are usually retained and a number of new centers are opened. The conditional <span><math><mi>p</mi></math></span>-next center problem involves both of these two aspects that arise in practice and, to the best of our knowledge, has not been considered in the literature so far. Since the CPNCP is NP-hard, a metaheuristic algorithm based on the Variable Neighborhood Search is developed. The proposed VNS includes an efficient implementation of the Fast Interchange heuristic which enables the VNS to tackle with real-life problem dimensions. The exhaustive computational experiments were performed on the modified PNCP test instances from the literature with up to 900 nodes. The obtained results are compared with the results of the exact solver CPLEX. It is shown that the proposed VNS reaches optimal solutions or improves the feasible ones provided by CPLEX in a significantly shorter CPU time. The VNS also quickly returns its best solutions when CPLEX failed to provide a feasible one. In order to investigate the effects of two different approaches in service network planning, the VNS solutions of the CPNCP are compared with the optimal or best-known solutions of the <span><math><mi>p</mi></math></span>-next center problem. In addition, the conducted computational study includes direct comparisons of the results obtained when the proposed SVNS is applied to PNCP (by setting the number of existing centers to 0) with the results of recent solution methods proposed for the PNCP.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"175 ","pages":"Article 106916"},"PeriodicalIF":4.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lexicographic optimization-based approaches to learning a representative model for multi-criteria sorting with non-monotonic criteria 基于词典优化的非单调标准多准则排序代表性模型学习方法

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-26 DOI: 10.1016/j.cor.2024.106917

Zhen Zhang , Zhuolin Li , Wenyu Yu

Deriving a representative model using value function-based methods from the perspective of preference disaggregation has emerged as a prominent and growing topic in multi-criteria sorting (MCS) problems. A noteworthy observation is that many existing approaches to learning a representative model for MCS problems traditionally assume the monotonicity of criteria, which may not always align with the complexities found in real-world MCS scenarios. Consequently, this paper proposes some approaches to learning a representative model for MCS problems with non-monotonic criteria through the integration of the threshold-based value-driven sorting procedure. To do so, we first define some transformation functions to map the marginal values and category thresholds into a UTA-like functional space. Subsequently, we construct constraint sets to model non-monotonic criteria in MCS problems and develop optimization models to check and rectify the inconsistency of the decision maker’s assignment example preference information. By simultaneously considering the complexity and discriminative power of the models, two distinct lexicographic optimization-based approaches are developed to derive a representative model for MCS problems with non-monotonic criteria. Eventually, we offer an illustrative example and conduct comprehensive simulation experiments to elaborate the feasibility and validity of the proposed approaches.

从偏好分解的角度出发，利用基于价值函数的方法推导具有代表性的模型，已成为多准则排序问题中一个突出而日益增长的课题。一个值得注意的观察是，许多现有的学习MCS问题的代表性模型的方法传统上假设标准的单调性，这可能并不总是与现实世界MCS场景中的复杂性相一致。因此，本文提出了一些通过整合基于阈值的值驱动排序过程来学习具有非单调准则的MCS问题的代表性模型的方法。为此，我们首先定义一些转换函数，将边际值和类别阈值映射到一个类似uta的功能空间。随后，我们构建约束集来模拟MCS问题中的非单调准则，并建立优化模型来检查和纠正决策者分配示例偏好信息的不一致性。通过同时考虑模型的复杂性和判别能力，提出了两种不同的基于词典学的优化方法，推导出具有非单调准则的MCS问题的代表性模型。最后，我们提供了一个说明性的例子，并进行了全面的仿真实验来阐述所提出方法的可行性和有效性。

{"title":"Lexicographic optimization-based approaches to learning a representative model for multi-criteria sorting with non-monotonic criteria","authors":"Zhen Zhang , Zhuolin Li , Wenyu Yu","doi":"10.1016/j.cor.2024.106917","DOIUrl":"10.1016/j.cor.2024.106917","url":null,"abstract":"<div><div>Deriving a representative model using value function-based methods from the perspective of preference disaggregation has emerged as a prominent and growing topic in multi-criteria sorting (MCS) problems. A noteworthy observation is that many existing approaches to learning a representative model for MCS problems traditionally assume the monotonicity of criteria, which may not always align with the complexities found in real-world MCS scenarios. Consequently, this paper proposes some approaches to learning a representative model for MCS problems with non-monotonic criteria through the integration of the threshold-based value-driven sorting procedure. To do so, we first define some transformation functions to map the marginal values and category thresholds into a UTA-like functional space. Subsequently, we construct constraint sets to model non-monotonic criteria in MCS problems and develop optimization models to check and rectify the inconsistency of the decision maker’s assignment example preference information. By simultaneously considering the complexity and discriminative power of the models, two distinct lexicographic optimization-based approaches are developed to derive a representative model for MCS problems with non-monotonic criteria. Eventually, we offer an illustrative example and conduct comprehensive simulation experiments to elaborate the feasibility and validity of the proposed approaches.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"175 ","pages":"Article 106917"},"PeriodicalIF":4.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Portfolio optimisation: Bridging the gap between theory and practice 投资组合优化：弥合理论与实践之间的差距

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-26 DOI: 10.1016/j.cor.2024.106918

Cristiano Arbex Valle

Portfolio optimisation is essential in quantitative investing, but its implementation faces several practical difficulties. One particular challenge is converting optimal portfolio weights into real-life trades in the presence of realistic features, such as transaction costs and integral lots. This is especially important in automated trading, where the entire process happens without human intervention.

Several works in literature have extended portfolio optimisation models to account for these features. In this paper, we highlight and illustrate difficulties faced when employing the existing literature in a practical setting, such as computational intractability, numerical imprecision and modelling trade-offs. We then propose a two-stage framework as an alternative approach to address this issue. Its goal is to optimise portfolio weights in the first stage and to generate realistic trades in the second. Through extensive computational experiments, we show that our approach not only mitigates the difficulties discussed above but also can be successfully employed in a realistic scenario.

By splitting the problem in two, we are able to incorporate new features without adding too much complexity to any single model. With this in mind we model two novel features that are critical to many investment strategies: first, we integrate two classes of assets, futures contracts and equities, into a single framework, with an example illustrating how this can help portfolio managers in enhancing investment strategies. Second, we account for borrowing costs in short positions, which have so far been neglected in literature but which significantly impact profits in long/short strategies. Even with these new features, our two-stage approach still effectively converts optimal portfolios into actionable trades.

投资组合优化在量化投资中是必不可少的，但其实施面临着一些实际困难。其中一个特别的挑战是，在交易成本和整手等现实特征存在的情况下，将最优投资组合权重转换为现实交易。这在自动交易中尤其重要，因为整个过程都是在没有人为干预的情况下进行的。文献中的一些作品扩展了投资组合优化模型来解释这些特征。在本文中，我们强调并说明了在实际环境中使用现有文献时面临的困难，例如计算难解性、数值不精确和建模权衡。然后，我们提出了一个两阶段框架作为解决这个问题的替代方法。它的目标是在第一阶段优化投资组合权重，在第二阶段产生现实的交易。通过大量的计算实验，我们表明我们的方法不仅减轻了上述困难，而且可以成功地应用于现实场景。通过将问题一分为二，我们能够在不给任何单一模型增加太多复杂性的情况下合并新的特征。考虑到这一点，我们对两个对许多投资策略至关重要的新特征进行了建模：首先，我们将两类资产，期货合约和股票，整合到一个单一的框架中，并举例说明这如何帮助投资组合经理提高投资策略。其次，我们考虑了空头头寸的借贷成本，这一点迄今为止在文献中被忽视，但它对多头/空头策略的利润产生了重大影响。即使有了这些新功能，我们的两阶段方法仍然有效地将最佳投资组合转化为可操作的交易。

{"title":"Portfolio optimisation: Bridging the gap between theory and practice","authors":"Cristiano Arbex Valle","doi":"10.1016/j.cor.2024.106918","DOIUrl":"10.1016/j.cor.2024.106918","url":null,"abstract":"<div><div>Portfolio optimisation is essential in quantitative investing, but its implementation faces several practical difficulties. One particular challenge is converting optimal portfolio weights into real-life trades in the presence of realistic features, such as transaction costs and integral lots. This is especially important in automated trading, where the entire process happens without human intervention.</div><div>Several works in literature have extended portfolio optimisation models to account for these features. In this paper, we highlight and illustrate difficulties faced when employing the existing literature in a practical setting, such as computational intractability, numerical imprecision and modelling trade-offs. We then propose a two-stage framework as an alternative approach to address this issue. Its goal is to optimise portfolio weights in the first stage and to generate realistic trades in the second. Through extensive computational experiments, we show that our approach not only mitigates the difficulties discussed above but also can be successfully employed in a realistic scenario.</div><div>By splitting the problem in two, we are able to incorporate new features without adding too much complexity to any single model. With this in mind we model two novel features that are critical to many investment strategies: first, we integrate two classes of assets, futures contracts and equities, into a single framework, with an example illustrating how this can help portfolio managers in enhancing investment strategies. Second, we account for borrowing costs in short positions, which have so far been neglected in literature but which significantly impact profits in long/short strategies. Even with these new features, our two-stage approach still effectively converts optimal portfolios into actionable trades.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"175 ","pages":"Article 106918"},"PeriodicalIF":4.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Q-learning driven multi-objective evolutionary algorithm for worker fatigue dual-resource-constrained distributed hybrid flow shop 基于q学习驱动的工人疲劳双资源约束分布式混合流水车间多目标进化算法

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-26 DOI: 10.1016/j.cor.2024.106919

Haonan Song , Junqing Li , Zhaosheng Du , Xin Yu , Ying Xu , Zhixin Zheng , Jiake Li

In practical industrial production, workers are often critical resources in manufacturing systems. However, few studies have considered the level of worker fatigue when assigning resources and arranging tasks, which has a negative impact on productivity. To fill this gap, the distributed hybrid flow shop scheduling problem with dual-resource constraints considering worker fatigue (DHFSPW) is introduced in this study. Due to the complexity and diversity of distributed manufacturing and multi-objective, a Q-learning driven multi-objective evolutionary algorithm (QMOEA) is proposed to optimize both the makespan and total energy consumption of the DHFSPW at the same time. In QMOEA, solutions are represented by a four-dimensional vector, and a decoding heuristic that accounts for real-time worker productivity is proposed. Additionally, three problem-specific initialization heuristics are developed to enhance convergence and diversity capabilities. Moreover, encoding-based crossover, mirror crossover and balanced mutation methods are presented to improve the algorithm’s exploitation capabilities. Furthermore, a Q-learning based local search is employed to explore promising nondominated solutions across different dimensions. Finally, the QMOEA is assessed using a set of randomly generated instances, and a detailed comparison with state-of-the-art algorithms is performed to demonstrate its efficiency and robustness.

在实际的工业生产中，工人往往是制造系统的关键资源。然而，很少有研究在分配资源和安排任务时考虑到工人的疲劳程度，这对生产力有负面影响。为了填补这一空白，本文引入了考虑工人疲劳的双资源约束的分布式混合流水车间调度问题。针对分布式制造的复杂性、多样性和多目标特性，提出了一种q学习驱动的多目标进化算法（QMOEA）来同时优化DHFSPW的完工时间和总能耗。在QMOEA中，解由一个四维向量表示，并提出了一种考虑实时工人生产率的解码启发式。此外，本文还开发了三种针对特定问题的初始化启发式方法，以增强收敛性和多样性能力。提出了基于编码的交叉、镜像交叉和平衡突变方法，提高了算法的利用能力。此外，采用基于q学习的局部搜索来探索跨不同维度的有前途的非主导解决方案。最后，使用一组随机生成的实例对QMOEA进行了评估，并与最先进的算法进行了详细的比较，以证明其效率和鲁棒性。

{"title":"A Q-learning driven multi-objective evolutionary algorithm for worker fatigue dual-resource-constrained distributed hybrid flow shop","authors":"Haonan Song , Junqing Li , Zhaosheng Du , Xin Yu , Ying Xu , Zhixin Zheng , Jiake Li","doi":"10.1016/j.cor.2024.106919","DOIUrl":"10.1016/j.cor.2024.106919","url":null,"abstract":"<div><div>In practical industrial production, workers are often critical resources in manufacturing systems. However, few studies have considered the level of worker fatigue when assigning resources and arranging tasks, which has a negative impact on productivity. To fill this gap, the distributed hybrid flow shop scheduling problem with dual-resource constraints considering worker fatigue (DHFSPW) is introduced in this study. Due to the complexity and diversity of distributed manufacturing and multi-objective, a Q-learning driven multi-objective evolutionary algorithm (QMOEA) is proposed to optimize both the makespan and total energy consumption of the DHFSPW at the same time. In QMOEA, solutions are represented by a four-dimensional vector, and a decoding heuristic that accounts for real-time worker productivity is proposed. Additionally, three problem-specific initialization heuristics are developed to enhance convergence and diversity capabilities. Moreover, encoding-based crossover, mirror crossover and balanced mutation methods are presented to improve the algorithm’s exploitation capabilities. Furthermore, a Q-learning based local search is employed to explore promising nondominated solutions across different dimensions. Finally, the QMOEA is assessed using a set of randomly generated instances, and a detailed comparison with state-of-the-art algorithms is performed to demonstrate its efficiency and robustness.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"175 ","pages":"Article 106919"},"PeriodicalIF":4.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Understand your decision rather than your model prescription: Towards explainable deep learning approaches for commodity procurement 了解您的决策，而不是您的模型处方：为商品采购开发可解释的深度学习方法

IF 4.1 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Operations Research

Pub Date : 2024-11-22 DOI: 10.1016/j.cor.2024.106905

Moritz Rettinger , Stefan Minner , Jenny Birzl

Hedging against price increases is particularly important in times of significant market uncertainty and price volatility. For commodity procuring firms, futures contracts are a widespread means of financially hedging price risks. Recently, digital data-driven decision-support approaches have been developed, with deep learning-based methods achieving outstanding results in capturing non-linear relationships between external features and price trends. Digital procurement systems leverage targeted purchasing decisions of these optimization models, yet the decision-mechanisms are opaque. We employ a prescriptive deep-learning approach modeling hedging decisions as a multi-label time series classification problem. We backtest the performance in two evaluation periods, i. e., 2018–2020 and 2021–2023, for natural gas, crude oil, nickel, and copper. The approach performs well in the first evaluation period of the testing framework yet fails to capture market disruptions (pandemic, geopolitical developments) in the second evaluation period, yielding significant hedging losses or degenerating into a simple hand-to-mouth procurement policy. We employ explainable artificial intelligence to analyze the performance for both periods. The results show that the models cannot handle market regime switches and disruptive events within the considered feature set.

在市场严重不确定和价格波动时，对冲价格上涨的风险尤为重要。对于大宗商品采购公司来说，期货合约是一种广泛的金融对冲价格风险的手段。最近，数字数据驱动的决策支持方法得到了发展，其中基于深度学习的方法在捕捉外部特征与价格趋势之间的非线性关系方面取得了突出成果。数字采购系统利用这些优化模型做出有针对性的采购决策，但决策机制并不透明。我们采用了一种规范性深度学习方法，将对冲决策建模为多标签时间序列分类问题。我们在两个评估期（即 2018-2020 年和 2021-2023 年）对天然气、原油、镍和铜的性能进行了回溯测试。该方法在测试框架的第一个评估期表现良好，但在第二个评估期未能捕捉到市场干扰（大流行病、地缘政治发展），导致重大对冲损失或沦为简单的手到擒来采购政策。我们采用可解释人工智能来分析这两个时期的表现。结果表明，在所考虑的特征集中，模型无法处理市场制度转换和破坏性事件。

{"title":"Understand your decision rather than your model prescription: Towards explainable deep learning approaches for commodity procurement","authors":"Moritz Rettinger , Stefan Minner , Jenny Birzl","doi":"10.1016/j.cor.2024.106905","DOIUrl":"10.1016/j.cor.2024.106905","url":null,"abstract":"<div><div>Hedging against price increases is particularly important in times of significant market uncertainty and price volatility. For commodity procuring firms, futures contracts are a widespread means of financially hedging price risks. Recently, digital data-driven decision-support approaches have been developed, with deep learning-based methods achieving outstanding results in capturing non-linear relationships between external features and price trends. Digital procurement systems leverage targeted purchasing decisions of these optimization models, yet the decision-mechanisms are opaque. We employ a prescriptive deep-learning approach modeling hedging decisions as a multi-label time series classification problem. We backtest the performance in two evaluation periods, i.e., 2018–2020 and 2021–2023, for natural gas, crude oil, nickel, and copper. The approach performs well in the first evaluation period of the testing framework yet fails to capture market disruptions (pandemic, geopolitical developments) in the second evaluation period, yielding significant hedging losses or degenerating into a simple hand-to-mouth procurement policy. We employ explainable artificial intelligence to analyze the performance for both periods. The results show that the models cannot handle market regime switches and disruptive events within the considered feature set.</div></div>","PeriodicalId":10542,"journal":{"name":"Computers & Operations Research","volume":"175 ","pages":"Article 106905"},"PeriodicalIF":4.1,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142701940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0