http://hdl.handle.net/2451/14093 Sat, 11 Apr 2026 16:24:53 GMT 2026-04-11T16:24:53Z http://hdl.handle.net/2451/43902 Title: Inventory Policies and Information Sharing: An Efficient Frontier Approach Authors: Caldentey, Rene; Giloni, Avi; Hurvich, Clifford Abstract: We consider a two-tier inventory management system with one retailer and one supplier. The retailer serves a demand driven by a stationary moving average process (of possibly infinite order) and places periodic inventory replenishment orders to the supplier. In this setting, we study the value of information sharing and its impact on the retailer’s optimal ordering strategy. We argue that information sharing affects performance through two key cost drivers: (i) on-hand inventory variability and (ii) replenishment order variability. We characterize a “Pareto frontier” between these two sources of variability by identifying optimal inventory replenishment strategies that trade-off one type of variability for the other in a cost efficient way. For the case in which the retailer is able to share her complete demand history, we provide a full characterization of the efficient frontier, as well as of an optimal replenishment policy. On the other hand, when the retailer is not able (or willing) to share any demand information we provide a partial characterization of an optimal solution and show that information sharing does not always add value. We also show that the question of identifying conditions under which information sharing does offer value reduces to a delicate analysis of the invertibility (in a time series sense) of a specific stationary process. Fri, 01 Mar 2019 00:00:00 GMT http://hdl.handle.net/2451/43902 2019-03-01T00:00:00Z http://hdl.handle.net/2451/41679 Title: Aggregated Information in Supply Chains Authors: Kovtun, Vladimir; Giloni, Avi; Hurvich, Clifford Abstract: We study a two-stage supply chain where the retailer observes two demand streams coming from two consumer populations. We further assume that each demand sequence is a station- ary Autoregressive Moving Average (ARMA) process with respect to a Gaussian white noise sequence (shocks). The shock sequences for the two populations could be contemporaneously correlated. We show that it is typically optimal for the retailer to construct its order to its supplier based on forecasts for each demand stream (as opposed to the sum of the streams) and that doing so is never sub-optimal. We demonstrate that the retailer’s order to its supplier is ARMA and yet can be constructed as the sum of two ARMA order processes based upon the two populations. When there is no information sharing, the supplier only observes the retailer’s order which is the aggregate of the two aforementioned processes. In this paper, we determine when there is value to sharing the retailer’s individual orders, and when there is additional value to sharing the retailer’s individual shock sequences. We also determine the supplier’s mean squared forecast error under no sharing, process sharing, and shock sharing. Thu, 08 Feb 2018 00:00:00 GMT http://hdl.handle.net/2451/41679 2018-02-08T00:00:00Z http://hdl.handle.net/2451/34464 Title: Impact of Exponential Smoothing on Inventory Costs in Supply Chains Authors: Hsieh, Meng-Chen; Giloni, Avi; Hurvich, Clifford Abstract: It is common for firms to forecast stationary demand using simple exponential smoothing due to the ease of computation and understanding of the methodology. In this paper we show that the use of this methodology can be extremely costly in the context of inventory in a two-stage supply chain when the retailer faces AR(1) demand. We show that under the myopic order-up-to level policy, a retailer using exponential smoothing may have expected inventory-related costs more than ten times higher than when compared to using the optimal forecast. We demonstrate that when the AR(1) coefficient is less than the exponential smoothing parameter, the supplier’s expected inventory-related cost is less when the retailer uses optimal forecasting as opposed to exponential smoothing. We show there exists an additional set of cases where the sum of the expected inventory-related costs of the retailer and the supplier is less when the retailer uses optimal forecasting as opposed to exponential smoothing even though the supplier’s expected cost is higher. In this paper, we study the impact on the naive retailer, the sophisticated supplier, and the two-stage chain as a whole of the supplier sharing its forecasting expertise with the retailer. We provide explicit formulas for the supplier’s demand and the mean squared forecast errors for both players under various scenarios. Wed, 03 Feb 2016 00:00:00 GMT http://hdl.handle.net/2451/34464 2016-02-03T00:00:00Z http://hdl.handle.net/2451/27726 Title: A Column Generation Algorithm for Choice-Based Network Revenue Management Authors: Bront, Juan Jose Miranda Abstract: In the last few years, there has been a trend to enrich traditional revenue management models built upon the independent demand paradigm by accounting for customer choice behavior. This extension involves both modeling and computational challenges. One way to describe choice behavior is to assume that each customer belongs to a segment, which is characterized by a consideration set, i.e., a subset of the products provided by the firm that a customer views as options. Customers choose a particular product according to a multinomial-logit criterion, a model widely used in the marketing literature. In this paper, we consider the choice-based, deterministic, linear programming model (CDLP) of Gallego et al. [6], and the follow-up dynamic programming (DP) decomposition heuristic of van Ryzin and Liu [16], and focus on the more general version of these models, where customers belong to overlapping segments. To solve the CDLP for real-size networks, we need to develop a column generation algorithm. We prove that the associated column generation subproblem is indeed NP-Complete, and propose a simple, greedy heuristic to overcome the complexity of an exact algorithm. Our computational results show that the heuristic is quite effective, and that the overall approach has good practical potential and leads to high quality solutions. Mon, 13 Oct 2008 20:26:02 GMT http://hdl.handle.net/2451/27726 2008-10-13T20:26:02Z