Operations Research eJournal最新文献_第2页

Deposit and Withdrawal Dynamics: A Data-Based Mutually-Exciting Stochastic Model 存取款动态:一个基于数据的相互激励随机模型

Operations Research eJournal Pub Date : 2020-08-19 DOI: 10.2139/ssrn.3665436

Yuqian Xu, Lingjiong Zhu, Haixu Wang

{"title":"Deposit and Withdrawal Dynamics: A Data-Based Mutually-Exciting Stochastic Model","authors":"Yuqian Xu, Lingjiong Zhu, Haixu Wang","doi":"10.2139/ssrn.3665436","DOIUrl":"https://doi.org/10.2139/ssrn.3665436","url":null,"abstract":"This paper proposes a mutually exciting discrete-time stochastic model to capture two essential features underlying the bank-customer behavior process---the dependence on the past behavior (i.e., path-dependence) and the behavioral interdependence between deposit and withdrawal activities (i.e., mutual excitation). In reality, despite the existence of large-scale data sources, the granular information contained in the data set can still be limited, for instance, aggregated versus individual activities. If the data are observed in an aggregated format, existing continuous-time models with mutually exciting and path-dependence features (e.g., a Hawkes-type model) cannot be directly applied. We thus propose a novel discrete-time stochastic model to tackle this practical and technical challenge. Despite the challenge, we are able to fully characterize the probability distribution for the customer deposit and withdrawal likelihood (i.e., the closed-form characteristic functions under the discrete-time setting), and hence we are able to theoretically quantify customer performance measures (i.e., churn probability, long-term average account value, and liquidity risk) and establish efficient maximum likelihood estimation. To validate the performance of our proposed model, we calibrate it with a customer deposit and withdrawal data set from one leading online money market fund. We compare our model with classic time-series and machine-learning models and show that our model is able to achieve high prediction accuracy. The theoretical tractability and predictive accuracy enable us to build optimization models for improving firm performance, and we illustrate one application through a personalized interest-rate optimization problem. On a broader note, our model framework is generally applicable to characterize any time-series data with path-dependence, mutual excitation, and aggregated observation (i.e., discrete-time) in nature, and to inform optimal policies for decision makers.","PeriodicalId":275253,"journal":{"name":"Operations Research eJournal","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116460401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Robust Dynamic Pricing with Demand Learning in the Presence of Outlier Customers 存在离群客户时具有需求学习的鲁棒动态定价

Operations Research eJournal Pub Date : 2020-07-14 DOI: 10.2139/ssrn.3650656

Xi Chen, Yining Wang

引用次数: 4

Information Visibility in Omnichannel Queues 全通道队列中的信息可见性

Operations Research eJournal Pub Date : 2020-07-10 DOI: 10.2139/ssrn.3485810

Ricky Roet-Green, Yuting Yuan

{"title":"Information Visibility in Omnichannel Queues","authors":"Ricky Roet-Green, Yuting Yuan","doi":"10.2139/ssrn.3485810","DOIUrl":"https://doi.org/10.2139/ssrn.3485810","url":null,"abstract":"Omnichannel system is a common operation strategy which provides multiple ways for customers to experience the business. One feature of such system is the information heterogeneity across channels. For example, to customers, the queue length in the physical store is visible, while the queue length in the online ordering channel is invisible. We study customers’ decision making in an omnichannel system with partially observable queue. In such system, customers only observe the length of visible queue. In particular, we examine partially observable queueing models with two types of disciplines: (1) FCFS; (2) visible-class priority. With fully observable system as a benchmark, we disentangle the performance difference between any partially observable system and the benchmark system into three effects: trick, shift and scare-away. We find that when market sizes under fully and partially observable systems are comparable, partially observable system generates higher throughput if customers are not scared away by invisibility. Surprisingly, even with less information, partially observable system can have higher social welfare when the invisible arrival rate is high. In that case, the customers are scared away and the system becomes less congested.","PeriodicalId":275253,"journal":{"name":"Operations Research eJournal","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126344295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Optimal Control of Service Systems with Heterogeneous Servers and Priority Customers 具有异构服务器和优先客户的服务系统的最优控制

Operations Research eJournal Pub Date : 2020-06-16 DOI: 10.2139/ssrn.3628440

David Chen, Ruoran Chen, Rowan Wang, Xuan Wang

引用次数: 0

A Non-Parametric Approach for Setting Safety Stock Levels 安全库存水平设定的非参数方法

Operations Research eJournal Pub Date : 2020-06-11 DOI: 10.2139/ssrn.3624998

John P. Saldanha, Bradley S. Price, Douglas J. Thomas

{"title":"A Non-Parametric Approach for Setting Safety Stock Levels","authors":"John P. Saldanha, Bradley S. Price, Douglas J. Thomas","doi":"10.2139/ssrn.3624998","DOIUrl":"https://doi.org/10.2139/ssrn.3624998","url":null,"abstract":"In practice, lead time demand (LTD) can be non-standard: skewed, multi-modal or highly variable; factors that compromise the validity of the classic approaches for setting safety stock levels. Motivated by encountering this problem at our industry partner, we develop an approach for setting safety stock levels using the bootstrap, a widely-used statistical procedure. We extend prior research that has used the bootstrap for quantile estimation to address the multi-parameter estimation of safety stocks. We develop a multivariate central limit theorem for the bootstrap mean and bootstrap quantile -- components of the safety stock calculation -- highlighting why the generalization of these bootstrap methods is critical for inventory management. These results provide a theoretical underpinning for the bootstrap estimator of safety stock and permit the construction of confidence intervals for safety stock estimates, allowing decision makers to understand the reliability with which the desired service level will be achieved. Building on our theoretical results, and supported by numerical experiments, we provide insights on the behavior of the bootstrap for various LTD distributions, which our results demonstrate are critical when employing the bootstrap method. Implementation results with our industry partner indicate our approach is quite effective in setting safety stock levels.","PeriodicalId":275253,"journal":{"name":"Operations Research eJournal","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131361891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Constrained Assortment Optimization Under the Mixed Logit Model with Design Options 具有设计选项的混合Logit模型下的约束分类优化

Operations Research eJournal Pub Date : 2020-06-11 DOI: 10.2139/ssrn.3624816

K. Haase, Sven Müller

引用次数: 0

Pricing with Consumer Sequential Choice Model and Its Application in the Design of a Threshold-Type Promotion 消费者顺序选择定价模型及其在阈值型促销设计中的应用

Operations Research eJournal Pub Date : 2020-05-31 DOI: 10.2139/ssrn.3623031

Zhenzhen Yan

{"title":"Pricing with Consumer Sequential Choice Model and Its Application in the Design of a Threshold-Type Promotion","authors":"Zhenzhen Yan","doi":"10.2139/ssrn.3623031","DOIUrl":"https://doi.org/10.2139/ssrn.3623031","url":null,"abstract":"A threshold-type promotion is to discount items by a flat dollar amount when a consumer’s total consumption level exceeds a given threshold. The goal of this paper is to understand the effect of the promotion on companies’ sales and profit and propose a data-driven approach to jointly price items and optimize the promotion decisions. We propose a novel sequential choice model to characterize a consumer’s choice of multiple items in a single transaction. The sequential choice model generalizes the traditional choice model, which assumes at most one item chosen in one transaction. Based on that, we establish a general convex pricing optimization framework under mild conditions. We further show that the threshold-type promotion problem fits in the framework with an extra set of pricing constraints. Finally, we provide a data-driven approach based on the proposed pricing model to solve a joint pricing and promotion design problem. Under the assumption of exponential marginals, we estimate the choice model from sales data by a linear program and obtain the optimal price and promotion by solving a mixed-integer linear program. Finally, several numerical studies are conducted to test the efficiency of the framework and understand the effect of promotion on companies’ profit.","PeriodicalId":275253,"journal":{"name":"Operations Research eJournal","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127617195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distributionally Robust Optimization under Distorted Expectations 扭曲期望下的分布鲁棒优化

Operations Research eJournal Pub Date : 2020-03-30 DOI: 10.2139/ssrn.3566708

Jun Cai, Jonathan Yu-Meng Li, Tiantian Mao

{"title":"Distributionally Robust Optimization under Distorted Expectations","authors":"Jun Cai, Jonathan Yu-Meng Li, Tiantian Mao","doi":"10.2139/ssrn.3566708","DOIUrl":"https://doi.org/10.2139/ssrn.3566708","url":null,"abstract":"Optimal Decision Making Under Distorted Expectation with Partial Distribution Information Decision makers who are not risk neutral may evaluate expected values by distorting objective probabilities to reflect their risk attitudes, a phenomenon known as distorted expectations. This concept is widely applied in behavioral economics, insurance, finance, and other business domains. In “Distributionally Robust Optimization Under Distorted Expectations,” Cai, Li, and Mao study how decision makers using distorted expectations can optimize their decisions when only partial information about objective probabilities is available. They show that decision makers who are ambiguity averse can optimize their decisions as if they are risk averse with their risk attitudes characterized by a convex distortion function. This finding demonstrates why even non–risk-averse decision makers, such as those studied in the celebrated cumulative prospect theory, may consider it optimal to take risk-averse decisions when facing uncertainty about objective probabilities. Leveraging this finding, the authors show that a large class of distributionally robust optimization problems involving the use of distorted expectations can be tractably solved as convex programs.","PeriodicalId":275253,"journal":{"name":"Operations Research eJournal","volume":"489 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116817673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Online Supplement to 'An Analysis of Voluntary Recycled Content Claims Under Demand Benefit and Uncertain Recycled Input Supply' “需求效益和不确定回收投入供给下的自愿回收成分声明分析”在线补充

Operations Research eJournal Pub Date : 2020-02-18 DOI: 10.2139/ssrn.3540363

A. Vedantam, Ananth V. Iyer

引用次数: 1

A Practitioner's Guide and MATLAB Toolbox for Mixed Frequency State Space Models 混合频率状态空间模型的从业者指南和MATLAB工具箱

Operations Research eJournal Pub Date : 2020-02-05 DOI: 10.2139/ssrn.3532455

Scott A. Brave, R. Butters, David Kelley

引用次数: 3