Forecasting market prices in a supply chain game

Predicting the uncertain and dynamic future of market conditions on the supply chain, as reflected in prices, is an essential component of effective operational decision-making. We present and evaluate methods used by our agent, Deep Maize, to forecast market prices in the trading agent competition supply chain management game (TAC/SCM). We employ a variety of machine learning and representational techniques to exploit as many types of information as possible, integrating well-known methods in novel ways. We evaluate these techniques through controlled experiments as well as performance in both the main TAC/SCM tournament and supplementary Prediction Challenge. Our prediction methods demonstrate strong performance in controlled experiments and achieved the best overall score in the Prediction Challenge.     

Learning approaches for developing successful seller strategies in dynamic supply chain management

Variable, dynamic pricing is a key characteristic of the modern electronic trading environments, allowing for prices that change or fluctuate due to uncertainty and different conditions and context. Being able to manage dynamic pricing strategies is vital for companies wishing to succeed in the world of modern business. The ability to accurately predict selling prices at a given time can help organizations to maximize their profit. This paper addresses the problem of predicting customer order prices and choosing the selling strategy which can lead to a greater profit in the context of supply chain management (SCM). The potential of the Neural Networks (NN) and Genetic Programming (GP) learning techniques is explored for making price forecasts. In particular, different parameter settings and methods for preprocessing input data are investigated in the paper. Although, both techniques showed the potential for dealing with the problem of dynamic pricing in SCM, NN models outperform GP models in the context under consideration in terms of accuracy of prediction, complexity of implementation, and execution time.     

Effect of change management capability in real-time environment: an information orientation perspective in supply chain management

Supply chain management (SCM) is an important strategic tool that requires careful planning and management. While the availability of real-time information is a critical aspect of an SCM system, it possesses a potential to disrupt supply chain participants. Thus, the success of an SCM system hinges on how well participants deal with changes taking place in a real-time environment. This study adopts the concept of the real-time enterprise to understand the role of change management on SCM performance based on the concept of the information orientation. The study empirically validated the role of change management on SCM performance.     

Emerging market structures in the digital supply chain

The supply chain for distributing digital goods via the Internet is in the process of spasmodic change. A wide array of new, high-speed access technologies are transforming the last mile, eroding the market power of established access providers, making smaller companies disappear overnight, and generating huge alliances. Customers face a rich set of options in access and content. The many access options and speeds have been accompanied by increasingly innovative digital products and services, most of them personalized. Wireless is maturing as a medium for data distribution with exciting new applications. While most observers recognize that the industries of content and access provision are in flux, it is unclear which business models may survive. The savvy organization (and individual) need to correctly interpret the implications of the dazzling developments in technology to effectively position themselves in the market. The authors characterize scenarios that are likely to occur based on the premise that you can't think of content and access provision as separate markets. Value-added bundles of dynamically customized content will be the order of the day. Will you and your organization be ready for the change?     

IT与供应链管理

随着市场竞争的加剧 ,供应链管理开始受到推崇。IT在促进供应链管理方面起着重要的作用。应用信息技术可以有效削弱供应链管理中的典型问题 -BW效应 ,提高供应链的运营水平。     

Supporting decisions in real-time enterprises: autonomic supply chain systems

Supporting decisions in real time has been the subject of a number of research efforts. This paper reviews the technology and architecture necessary to create an autonomic supply chain for a real-time enterprise for supply chain systems. The technologies weaved together include knowledge-based event managers, intelligent agents, radio frequency identification (RFID), database and system integration, and enterprise resource planning systems. This article is part of the “Handbook on Decision Support Systems” edited by Frada Burstein and Clyde W. Holsapple (2008) Springer.     

Supporting real-time supply chain decisions based on RFID data streams

While RFID technology has been widely praised for its ability to streamline supply chain processes, little attention has been given to its unique data capturing characteristics to support real-time decision making. Being able to efficiently perform complex real-time analysis on top of RFID event streams is a key challenge for modern applications. This provides management with a novel data analysis mechanism to allow better, tactical, on time, well-informed decisions. The two main issues in RFID data management (RFDM) concern expressibility (how to simply and concisely express stream queries) and performance (how to efficiently evaluate stream queries). In this paper we claim that a spreadsheet-like query model, where formulation is done in a column-wise fashion, can express intuitively a large class of useful and practical RFDM queries. We propose a simple SQL extension to do that and show how these queries can be evaluated efficiently. We finally discuss a prototype called COSTES (COntinuous SpreadsheeT-likE computations), which implements our SQL extensions and evaluation algorithms. Presentation takes place within the context of two representative RFID applications, namely shelf availability and in-store sales promotions.     

The impact of supply contracts on supply chain product-flow management

One of the performance issues faced by the supply chain (SC) is the competitive production and delivery of products to all partners of the SC. The supply contract linking the Original Equipment Manufacturer (OEM) with its suppliers currently represents an important decision tool influencing the production and delivery of final products.     

供应链协同管理的绩效评估

供应链协同管理是通过对供应链系统的人力、物力、资金及信息等资源的规划、组织和控制,来实现其目标。供应链协同管理的效果如何,可通过绩效评估进行检验,他是协同管理的一个重要环节。使用平衡积分卡、粗糙集中启发式属性约简的方法和BP神经网络的理论,探索建立了平衡积分卡、启发式属性约简和BP神经网络相结合的供应链协同管理的绩效评估模型。并结合一个实例,首先对其基于平衡记分卡的指标体系进行了约简,然后将约简的评价指标输入到BP神经网络中进行智能训练,最后把评估的样本输入到训练好的BP网络中得出供应链协同管理的绩效评估值,评估结果与实际结果基本吻合。     

Interactions of agents in performance based supply chain management

To acquire a competitive advantage in the expanding market, manufacturing companies should be able to manage their supply chain as much effective as possible. Measuring the supply chain performance is one of the main indicators of business success. Supply chain management (SCM) involves managing the flow of materials from suppliers to manufacturing units. This paper proposes a SCM model with performance measurement capabilities. The model is designed in such a way that it well suits to multi agent systems and related implementations. This paper highlights the components of the model especially pointing out the key parameters of performance indicators.     

供应链中供应商选择决策方法

为了克服传统供应商选择过程中面向单一解的局限性,更好地解决供应链中供应商选择的多目标优化问题,达到费用和效益最佳,以产品价格、质量、交货可靠性和交货提前期为评估指标,建立了供应商选择多目标优化模型.首次将SPEA2算法应用于供应商选择问题,构造了适合该模型特征的SPEA2算法求解过程,可针对多个求解目标获得一组均衡解.模拟算例中一次得到多组有效解,表明所建立模型及所用方法是有效、可行的,它为制造企业获得有多种解决方案的供应商选择问题提供了可参考的模型和求解算法.     

A study of emergency management of supply chain under supply disruption

Emergency is an important factor resulting in supply disruption risk. How to deal with emergency in supply chain arouses managers’ and researchers’ attention in recent years. In order to improve the effect of supply disruption risk management under this situation, this paper builds the supply disruption Emergency Management Model of supply chain from the angle of risk management and discusses whether the decision-making mechanism of the case-based reasoning can bring the better effect for supply disruption by using computational experiment. The results mainly show that the mechanism of risk assessment, risk identification, risk control and risk evaluation based on the case-based reasoning can effectively deal with supply disruption risk, and bring more profit and better service level for the members of supply chain.     

Intelligent supply chain management using adaptive critic learning

A set of neural networks is employed to develop control policies that are better than fixed, theoretically optimal policies, when applied to a combined physical inventory and distribution system in a nonstationary demand environment. Specifically, we show that model-based adaptive critic approximate dynamic programming techniques can be used with systems characterized by discrete valued states and controls. The control policies embodied by the trained neural networks outperformed the best, fixed policies (found by either linear programming or genetic algorithms) in a high-penalty cost environment with time-varying demand.     

考虑市场细分的闭环供应链生产与定价策略

基于市场细分建立闭环供应链模型,分析了决策变量随外生变量的变化规律,并比较了闭环供应链与不回收再制造情形的决策.结果表明:新制造和再制造产品的批发价随回购价的增加而增加,随回收价的增加而减少,零售价随回收价和回收努力程度的增加而增加;产品总量随消费者偏好系数的增加而增加,随再制造成本、回收努力程度及回收价的增加而减少;闭环供应链的新制造产品批发价和零售价均比不回收再制造时高;消费者偏好系数高于临界值时,回收再制造对于闭环供应链有利.     

A control model for object virtualization in supply chain management

Due to the emergence of the Internet of Things, supply chain control can increasingly be based on virtual objects instead of on the direct observation of physical objects. Object virtualization allows the decoupling of control activities from the handling and observing of physical products and resources. Moreover, virtual objects can be enriched with information that goes beyond human observation. This will allow for more advanced control capabilities, e.g. concerning tracking and tracing, quality monitoring and supply chain (re)planning. This paper proposes a control model for object virtualization in supply chain management, which is based on a multiple case study in the Dutch floriculture. It includes a typology of distinct mechanisms for object virtualization, which discerns reference objects and future projections next to the representation of real physical objects. The control model helps to define feasible redesign options for the virtualization of supply chain control. It is also of value as a basis to define the requirements for information systems that enable these redesign options.     

Accessing information sharing and information quality in supply chain management

This paper empirically examines the impact of environmental uncertainty, intra-organizational facilitators, and inter-organizational relationships on information sharing and information quality in supply chain management.Based on the data collected from 196 organizations, multiple regression analyses are used to test the factor impacting information sharing and information quality respectively. It is found that both information sharing and information quality are influenced positively by trust in supply chain partners and shared vision between supply chain partners, but negatively by supplier uncertainty. Top management has a positive impact on information sharing but has no impact on information quality. The results also show that information sharing and information quality are not impacted by customer uncertainty, technology uncertainty, commitment of supply chain partners, and IT enablers.Moreover, a discriminant analysis reveals that supplier uncertainty, shared vision between supply chain partners and commitment of supply chain partners are the three most important factors in discriminating between the organizations with high levels of information sharing and information quality and those with low levels of information sharing and information quality.     

A review of soft computing applications in supply chain management

It is broadly recognised by global companies that supply chain management is one of the major core competencies for an organisation to compete in the marketplace. Organisational strategies are mainly concentrated on improvement of customer service levels as well as reduction of operational costs in order to maintain profit margins. Therefore supply chain performance has attracted researchers’ attention. A variety of soft computing techniques including fuzzy logic and genetic algorithms have been employed to improve effectiveness and efficiency in various aspects of supply chain management. Meanwhile, an increasing number of papers have been published to address related issues. The aim of this paper is to summarise the findings by a systematic review of existing research papers concerning the application of soft computing techniques to supply chain management. Some areas in supply chain management that have rarely been exposed in existing papers, such as customer relationship management and reverse logistics, are therefore suggested for future research.     

集成供应链管理的多目标规划研究

目前,供应链管理已经成为学术研究的一个热点问题,也是企业战略管理的一项重要内容。为此首先使用多目标规划的方法描述了供应链及其成员的运作性能、供应链的协调运作、供应链成员的利润等,建立了由一个制造商和一个供应商构成的多产品、多阶段集成供应链管理绩效决策模型;其次通过应用算例的研究验证了模型的有效性和可行性;最后,针对各种参数的变化,对模型进行了灵敏度分析,并与分散供应链管理绩效决策模型进行了对照研究,为优化供应链绩效、拓展市场需求、开发原材料供应渠道提供了决策参考。