概率预期下在线报童问题的最小风险策略

报童问题是库存管理中一个基本模型。已有的报童模型主要利用均值-方差方法和期望效用目标方法进行风险的描述和度量。这些方法假设需求分布信息已知,而实际中需求分布信息往往难以完全刻画。本文使用概率预期作为刻画不完全需求分布信息的格式,基于在线风险补偿的思想,为需求分布信息不完全的报童问题建立了最小风险模型。使用该模型设计了最小风险策略,使报童可以根据自己设定的不同收益和未来概率预期选择最优订购量。     

基于库存价值改变和随机需求的经济订货批量模型

大多数库存研究的重点都集中在各种复杂的限制条件和模型的变换上.没有考虑到库存本身可能发生贬值或增值的情况,而实际中库存本身常常会发生价值变化.针对以往库存模型中没有考虑库存价值变化的问题,提出了在需求为随机连续分布、库存价值发生变化情况下的单周期经济订货批量模型,给出了最优订货策略.模型中以先进先出为假设条件,基于报童模型的思想,以订货量为决策变量、期望收益为目标函数,结合随机需求的分布情况得到最优订货量和最大期望收益,并给出了相应的数学证明.通过算例对模型进行说明,并对影响最优订货批量和最大期望收益的各个参数进行敏感性分析.     

报童问题的最优竞争比策略及其风险补偿模型

报童问题是库存管理中一个重要的模型。对报童问题在不同的目标函数和约束条件下的扩展模型已有了大量的研究。已有研究假设产品的需求分布已知,然而,在实际中完全刻画需求分布信息常常是很困难的,因此,部分信息下的报童模型研究近年越来越受到重视。在竞争比分析方法下,对报童问题进行了讨论,建立概率预期下风险补偿模型用于解决部分信息的报童问题。在确定性预期和基本概率预期下,分别为具有风险偏好的报童设计了最优订购策略,使报童可以根据自己不同的风险容忍度和未来预期选择订购策略。     

带有马尔可夫竞争因子的多产品报童模型

在竞争的环境下考虑多产品报童问题。为了刻画多产品间的竞争关系，本文利用马尔可夫链构建多产品的需求转移模型，并根据模型的转移概率矩阵提出马氏竞争因子和综合竞争力等核心概念，进而结合卷积公式和雅可比行列式，将竞争因子的概念纳入经典报童模型的框架，构建了带有马氏竞争因子的多产品报童模型，同时在该模型的理论基础上给出了新的决策机制。模型的数据实验表明：竞争因子对多产品库存系统的最优订购策略具有重要的影响，关于产品的综合竞争力为单调递增函数；将竞争因子纳入多产品库存系统的决策机制，可进一步拓展报童模型在实际应用领域中的适应性以及提高库存系统的优化与控制的效用。     

基于需求预测的短生命周期产品订货策略研究

本文针对短生命周期产品的特点,考虑与需求因子相关的库存短缺拖后和无形变质,根据缺货时间点、订货时间点与产品到达成熟期的时间点之间的关系,建立基于短生命周期产品需求预测的3种订货策略模型:乐观订货策略,悲观订货策略和中庸订货策略模型,对模型进行了分析求解,对最优解的存在性进行了证明.然后根据实际销售数据进行需求预测和算例分析,分析各因子对于总库存成本、订货量、短缺拖后量、销售损失量以及最优订货策略的影响.最后通过订货策略分析,分析各因子对于最优订货策略的影响,并将它们划分为3种订货策略影响因子,分析结果可以指导企业在不同因子水平情况下如何调整订货策略,以降低总库存成本.     

库存成本变化的VMI供应链协调

提出了库存成本变化的经济订货批量(EOQ)模型，基于该模型研究了库存成本变化时供应商管理库存(VMI)系统的最优协议问题。在该系统中，订货商和供应商达成缺货成本共担协议：当缺货发生时，供应商需要向订货商支付缺货补偿。订货商和供应商分散决策，订货商通过设计协议来减少其成本，而供应商通过制定补货决策来缩小自身成本。通过与传统系统和整合系统的比较，得出了库存成本变化时VMI系统的最优补货决策和缺货成本共担协议。采用数值算例验证了分析结果。结果表明，当且仅当供应商预期成本等于整合系统的最小总成本与固定缺货罚金之和时，VMI系统与整合系统具有相同的补货决策和系统绩效，即能够实现供应链协调。     

基于XGBoost算法的数据驱动单周期报童问题研究

求解单周期报童问题通常假设需求分布服从某一特定形式,通过历史数据预测需求并求解优化模型。尽管此假设可以简化分析,但它并不能反映随时间动态变化的真实需求分布,且不可避免地将历史估计预测误差传递给优化过程。为解决这一问题,本文提出了一种将估计和优化相结合的方法。该方法采用数据驱动计算权重的形式来处理与特征相关的需求不确定性,并引入XGBoost算法对具有非平稳需求的单周期报童问题进行求解。在观察到影响需求的特征后,该方法能直接确定最佳库存决策。本文对运营管理领域的贡献主要包括两个方面：1）提供了一种解决方案,将名为XGBoost的可扩展端到端树提升系统的机器学习算法集成到了单周期报童问题中。2）将该集成估计优化算法应用于不同目标服务水平和训练样本量的真实数据集,并与现有研究报童问题的几种标准方法进行比较,结果表明,该方法至少可以降低约5%的库存成本。     

基于ACC支付模式的供应链金融模型研究

在零售商存在资金不足和顾客需求随机情况下，以报童模型为基础，针对变质品构建了供应链金融问题和ACC支付模式（提前支付Advance、现金支付Cash和信用支付Credit）相结合的零售商订货模型，即零售商与供应商、融资机构合作条件下的模型。研究表明，零售商会随着最优订货批量和最低期望成本的增加和降低趋势，进而调整订货量，从而规避供大于求的风险，最终降低总的期望成本。同时供应商可以适当调整支付比例，让零售商来分担坏账和商品变质风险。     

基于似然估计的零售商库存鲁棒均值-风险模型

针对具有风险厌恶的零售商,建立了权衡期望利润和条件风险值（CVaR）的均值-风险库存优化模型,给出了离散需求分布不确定条件下能实现帕累托最优但具有较高保守性和非帕累托最优但具有较低保守性的两种鲁棒对应。针对不确定需求分布,在仅知历史需求样本数据情况下,应用统计推断理论构建了满足一定置信水平的基于似然估计的需求概率分布不确定集。在此基础上,运用拉格朗日对偶理论,将上述两种鲁棒对应模型转化为易于求解的凹优化问题,并证明了其与原问题的等价性。最后,针对实际案例进行了数值计算,分析了不同系统参数和样本规模对零售商最优库存决策及其运作绩效的影响,并给出了零售商期望利润和条件风险值两个目标权衡的帕累托有效前沿。结果表明,采用基于似然估计的鲁棒优化方法得到的零售商库存策略具有良好鲁棒性,能够有效抑制需求分布不确定性对零售商库存绩效的影响。而且,历史需求样本规模越大,鲁棒库存策略下的零售商运作绩效越接近最优情况。进一步,通过对比发现,两种鲁棒对应模型虽然保守性不同,但在最终库存策略上保持一致。     

带有能力约束的多元马氏需求报童模型

在随机需求环境下考虑带有能力约束的多产品报童问题.为了对多产品的需求进行预测,并度量其需求间的关系,本文首先建立了多元马氏需求模型.其次,在该模型的理论基础上,提出了带有能力约束的多元马氏需求报童模型,进而给出多产品的最优订购策略解.最后,利用期望需求状态的概率值及其截尾概率分析了模型最优解的性质.模型的结论表明,在能力约束的条件下,最优订购量关于左截尾概率单调递减,关于右截尾概率单调递增,而期望需求状态的概率值对最优订购量具有双重的特殊影响.     

On the benefits of operational flexibility in a distribution network with transshipment

We consider a centralized distribution network with multiple retailers who receive replenishment inventory to satisfy customer demand of the local markets. The operational flexibility of the network is defined as the opportunity that one retailer's excess inventory can be transferred to satisfy other retailers’ unmet customer demand due to stock-outs. A general modeling framework is developed to optimize retailers’ order quantities under any possible flexibility level of a stylized two-stage distribution network. We apply the framework to formulate and solve the transshipment problem of a distribution network with three retailers. Six typical flexibility levels are investigated to make the comparison study on the firm's profit performance under three ordering quantity policies: average demand, newsvendor order quantity, and optimal order quantity. We find that the operational flexibility and system optimization are complements to the firm's performance. The ordering policy with newsvendor ordering quantity can perform fairly well with moderate flexibility level when compared with the optimized ordering policy with full flexibility.     

Durability,Transit Lags,and Optimality of Inventory Management Decisions

Two laboratory experiments on a single‐echelon inventory task show that inventory durability interacts with transit lags to create order volatility that exceeds demand volatility. Thus, inventory durability and transit lags cause managers to deviate from inventory decision optimality. Durability creates a large increase in order volatility because players adjust orders insufficiently to reflect current inventory and backlogs, much as they adjust orders insufficiently to reflect holding and backlog costs in newsvendor studies (e.g., Schweitzer and Cachon 2000). Transit lags exacerbate non‐optimal ordering by interfering with players' ability to correct prior errors. Our results suggest that non‐optimal inventory decisions can be driven by inventory and supply chain characteristics, even in the absence of the coordination and information sharing problems studied by Croson et al. (2005) and Sterman (1989a,b). We also examine the influence of features related to personality. We find little evidence that the interactive effects of durability and transit lags are altered by need for cognition, impulsiveness, or locus of control, suggesting that these features make supply chain management extremely difficult. These results imply that retailers and their upstream partners must consider the characteristics of their product and supply chains when interpreting demand signals received from downstream partners.     

Mean–variance analysis of the newsvendor model with stockout cost

We study the risk-averse newsvendor model with a mean–variance objective function. We show that stockout cost has a significant impact on the newsvendor's optimal ordering decisions. In particular, with stockout cost, the risk-averse newsvendor does not necessarily order less than the risk-neutral newsvendor. We illustrate this finding analytically for the case where the demand follows the power distribution.     

Newsvendor Problems with Demand Shocks and Unknown Demand Distributions

In today's competitive market, demand volume and even the underlying demand distribution can change quickly for a newsvendor seller. We refer to sudden changes in demand distribution as demand shocks. When a newsvendor seller has limited demand distribution information and also experiences underlying demand shocks, the majority of existing methods for newsvendor problems may not work well since they either require demand distribution information or assume stationary demand distribution. We present a new, robust, and effective machine learning algorithm for newsvendor problems with demand shocks but without any demand distribution information. The algorithm needs only an approximate estimate of the lower and upper bounds of demand range; no other knowledge such as demand mean, variance, or distribution type is necessary. We establish the theoretical bounds that determine this machine learning algorithm's performance in handling demand shocks. Computational experiments show that this algorithm outperforms the traditional approaches in a variety of situations including large and frequent shocks of the demand mean. The method can also be used as a meta‐algorithm by incorporating other traditional approaches as experts. Working together, the original algorithm and the extended meta‐algorithm can help manufacturers and retailers better adapt their production and inventory control decisions in dynamic environments where demand information is limited and demand shocks are frequent      

Decision making in the newsvendor problem: A cross-national laboratory study

In this paper, we conduct a laboratory experiment using the classic newsvendor problem to examine cross-national differences in inventory ordering patterns between Chinese and American decision makers based on a theoretical examination of the role of the Doctrine of the Mean in Chinese decision making. Drawing on the theory of context-dependent preferences (specifically extremeness aversion), we also revisit the flat-maximum hypothesis of Bolton and Katok [12], i.e., “thinning the set of order options leads to newsvendor decisions that achieve a higher proportion of maximum expected profit.” The results show that the “pull-to-center” effect is more prominent for Chinese than Americans, i.e., average order quantities of Chinese subjects are closer to the anchor of mean demand than those of American subjects. Furthermore, we find that thinning the set of order options such that the optimal order quantity is a middle option, not an extreme option in the choice set, leads to better performance in newsvendor decisions, which complements the flat-maximum hypothesis.     

二级供应链系统的三阶段协同订货模型

生产商-销售商联合生产库存系统是供应链的一个重要组成部分。但是目前协同条件下的相关订货策略具有明显的局限性,容易丢失真正的最优策略。本文利用边际分析法,通过改变销售商相邻两次订货量的大小来分析生产商和销售商库存费用的变化,发现销售商的订货量与系统库存费用变化量的确存在一定的规律。并且,进一步可以推导出该类系统的最优订货策略的订货量必须符合“三阶段”规律。根据该特点,只需设置各个阶段的初始订货量和订货次数等6个决策变量就可以构建订货策略的数学模型。该模型与直接求解的数学模型相比,不仅变量减少,而且其求解也相对简单。最后,利用各个文献中常用的两个实例仿真进行对比分析,验证了该策略确实能够找出其他策略丢失的最优解。     

具有多元马氏需求的多产品多阶段库存优化模型

本文研究一类新的多产品库存控制策略,即具有多元马氏需求特征的多产品多阶段的订货点订货量(Q, R, SS)策略,该策略考虑市场需求在不同产品之间具有多元马氏转移特征,并考虑缺货因素设置安全库存。论文首先建立了多产品多阶段的多元马氏需求预测模型,并通过该模型确定了各种产品需求之间的关系。同时,在该模型的理论基础上,提出了多产品多阶段的总期望成本模型及其最优(Q, R, SS)策略,进而结合算例给出模型的最优策略的数值解。     

A Newsvendor Who Chooses Informational Effort

We study a newsvendor who can acquire the services of a forecaster, or, more generally, an information gatherer (IG) to improve his information about demand. When the IG's effort increases, does the average ex ante order quantity rise or fall? Do average ex post sales rise or fall? Improvements in information technology and in the services offered by forecasters provide motivation for the study of these questions. Much depends on our model of the IG and his efforts. We study an IG who sends a signal to a classic single‐period newsvendor. The signal defines the newsvendor's posterior probability distribution on the possible demands and the newsvendor uses that posterior to calculate the optimal order. Each of the possible posteriors is a scale/location transform of the same base distribution. When the IG works harder, the average scale parameter drops. Higher IG effort is always useful to the newsvendor. We show that there is a critical value of order cost. For costs on one side of this value more IG effort leads to a higher average ex ante order and for costs on the other side to a lower average order. But for all costs, more IG effort leads to higher average ex post sales. We obtain analogous results for a “regret‐averse” newsvendor who suffers a penalty that is a nonlinear function of the discrepancy between quantity ordered and true demand.     

Price-setting newsvendor with strategic consumers

We consider a newsvendor who sells a single product over a single season with the objective of determining both the selling price and stock quantity to maximize the expected profit. The customers are strategic and we consider two demand cases: additive and multiplicative. For each case, we derive the newsvendor׳s optimal decisions and demonstrate that neglecting the price-sensitivity of demand leads the newsvendor to make sub-optimal decisions. Moreover, we show that under certain conditions, strategic consumer behavior may positively affect the newsvendor׳s optimal expected profit in the additive demand case.