Informs Annual Meeting 2017

MD11

INFORMS Houston – 2017

3 - Risk Minimization in Robust Inventory Routing Problem Zheng Cui, Chinese University of Hong Kong, Hong Kong, zcui@se.cuhk.edu.hk, Daniel Zhuoyu Long, Jin Qi, Lianmin Zhang We study a finite horizon stochastic inventory routing problem. In this problem, the supplier acts as a central planner who determines the replenishment quantities as well as the times and routes to all customers. We allow ambiguity in the probability distribution of uncertain demand at each customer. To quantify the risk in fulling the demand, we propose a decision criterion called Collective Requirement Violation (CRV) Index, which takes into account both the frequency and magnitudes of violation. The whole problem can be formulated as a mixed integer programming problem and the exact optimal solution can be found effectively. We compare the performance of our solutions with several benchmarks. 4 - A Convex Optimization Approach for Computing Correlated Choice Probabilities with Many Alternatives Xiaobo Li, University of Minnesota, Minneapolis, MN, 55414, United States, lixx3195@umn.edu, Karthik Natarajan, Selin Damla Ahipasaoglu The Cross Moment model (CMM) has been proposed as an alternative to MNP when the covariance information is available. Computing the choice probabilities with many alternatives is challenging in CMM. We develop a simpler formulation as a representative agent model by maximizing over the choice probabilities in the unit simplex. We develop a simple first order gradient method with inexact line search to compute choice probabilities and establish local linear convergence of this algorithm. Numerical experiments show that this method can compute choice probabilities for a large number of alternatives within a reasonable amount of time while explicitly capturing the correlation information. 330B Social Responsibility in Sourcing Sponsored: Manufacturing & Service Oper Mgmt Sponsored Session Chair: Goker Aydin, Johns Hopkins University, Baltimore, MD, 21202, United States, goker.aydin@jhu.edu 1 - Supply Risk Mitigation via Supplier Diversification and Improvement: An Experimental Evaluation Basak Kalkanci, Georgia Institute of Technology, 3151 Stillhouse Creek Dr SE, Apt 25517, Atlanta, GA, 30339, United States, basak.kalkanci@scheller.gatech.edu We use lab experiments to evaluate two sourcing strategies developed for mitigating supply risks of a buyer firm with heterogeneous suppliers: dual sourcing and single sourcing with supplier improvement. We also develop behavioral theories to elucidate the decision-making process of the buyer more effectively. With dual sourcing, human buyers allocate orders between suppliers more evenly than theory and exhibit quantity hedging behavior. We propose and empirically validate a theory of order allocation error minimization to explain this phenomenon. Human buyers use supplier improvement relatively successfully, despite being subject to supplier selection errors due to bounded rationality. 2 - Coordinating Supply Chains via Advance-order Discounts, Minimum Order Quantities, and Delegations Prashant Chintapalli, University of California Los Angeles, Los Angeles, CA, United States, prashant.chintapalli.1@anderson.ucla.edu, Stephen M. Disney, Christopher S. Tang Buyers often place rush orders with suppliers only after they receive firm orders from their customers. Rush orders are coslty for both the parties because the supplier incurs higher production costs. We show that though an advance-order discount (AOD) contract alone cannot coordinate the supply chain, the contract when combined with pre-specified minimum-order-quantity as a qualifier for the buyer to avail the discount, can coordinate the supply chain. We analyze another contract in which the buyer delegates the inventory decisions to the supplier in return for a discount on all units procured. We find both the combined contracts coordinate the supply chain in a Pareto improving manner. MD10

3 - Curbing the Usage of Conflict Minerals: A Supply Network Perspective

Han Zhang, Student, Indiana University-Bloomington, Bloomington, IN, 47405, United States, hz8@indiana.edu, Goker Aydin, H. Sebastian Heese

Legislation and NGOs pressure manufacturers to disclose their sources of “conflict minerals” — natural resources whose trade might finance conflicts. We study the effect of such interventions, using a model of a supply network consisting of mines, smelters, and manufacturers. We show that imposing penalties on manufacturers alone is not sufficient to eliminate conflict minerals from supply chains, and that an industrial alliance to pool auditing costs among compliant manufacturers is effective in reducing the equilibrium quantity traded of non- certified metals.

MD11

332A Empirical Studies of Operational Quality Sponsored: Manufacturing & Service Oper Mgmt, Service Operations Sponsored Session Chair: Robert L. Bray, Northwestern University, IL, United States, robertlbray@gmail.com 1 - Show or Tell: A Tanzanian Mobile Money Field Experiment on the Impacts of SMS Messages on Agent Performance Christopher Parker, Penn State, State College, PA, United States, chris.parker@psu.edu, Jason Acimovic, David F. Drake, Karthik Balasubramanian Mobile money allows consumers without physical bank accounts to conduct financial transactions through a wireless provider’s network. Deposits and withdrawals are performed by agents who decide how much physical and electronic cash to stock each day in order to fulfill customer demands for deposits and withdrawals. We implement an experiment in Tanzania to test whether sending explicit recommendations for cash levels or informative estimates of transaction volume are better for reducing agents’ stockout rates. Treated agents had a lower proportion of days-stocked-out by 80 basis points as compared to the control group. We also investigate treatment heterogeneity using agent characteristics. 2 - Menu Costs and the Bullwhip Effect: Empirical Evidence Ioannis (Yannis) Stamatopoulos, The University of Texas at Austin, McCombs School of Business, Austin, TX, United States, Yannis.Stamos@mccombs.utexas.edu, Soheil Ghili We empirically study the question of whether lower menu costs (operational costs of pricing) at a brick and mortar retail store imply higher or lower sales variability, and hence higher or lower bullwhip. We develop a theory for this question and test it using a structural estimation approach on data from a natural experiment. 3 - Supply Chain Proximity on Product Quality Juan Serpa, McGill University, juan.serpa@mcgill.ca We xplore the effect of supply chain proximity on product quality. To study this relationship, we merge five independent data sources from the automotive industry, collecting (i) auto component failure rates, (ii) upstream component factory locations, (iii) downstream assembly plant locations, and (iv) product- level links connecting the upstream and downstream factories. Combining these datasets yields one of the most detailed supply chain samples ever created, detailing the flow of 27,807 products through 529 supplier factories and 175 assembly plants. We find that, on average, the defect rate of a component increases by 0.21 percent when the distance increases by 100 kilometers. 4 - How Does Servers’ Workload Impact Customer Lifetime Value? An Empirical Study Qiuping Yu, Kelley School of Business, Indiana University, 1309 E. Tenth Street, Bloomington, IN, 47405-1701, United States, qiupyu@indiana.edu, Masoud Kamalahmadi, Yong-Pin Zhou Using a rich data set from a casual dining restaurant chain, we explore how servers’ workload impact customer repurchasing behavior thus their lifetime value. Through counterfactual studies, we demonstrate its implication in firm’s staffing decisions.

239