Search

Recently, with the development of temporal knowledge graph technology, more and more Temporal Knowledge Graph Embedded (TKGE) models have been developed. The effectiveness of TKGE largely depends on the ability to model intrinsic relation patterns and capture specific information about entities and relations. However, existing approaches can capture only some of them with insufficient modeling capacity, and none has a “deep” architecture for modeling the entries in a quadruple at the same dimension. In this article, we propose a more powerful KGE framework named DuCape, which combines a dual quaternion and capsule network in modeling for the first time to make up for the defects of existing TKGE models. In dual quaternion vector space, the head entity learns a k-dimensional rigid transformation parametrized by relation and time, falling near its corresponding tail entity. Further, we employ the embeddings of entities, relations, and time trained from dual quaternion vector space as the input to capsule networks. Experimental results on several basic datasets show that the DuCape model constructed in this article is superior to existing state-of-the-art models. [ABSTRACT FROM AUTHOR]

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ejor.2008.05.002 Byline: Alper Sen (a), Alex X. Zhang (b) Keywords: Pricing; Dynamic pricing; Revenue management; Demand learning Abstract: For many industries (e.g., apparel retailing) managing demand through price adjustments is often the only tool left to companies once the replenishment decisions are made. A significant amount of uncertainty about the magnitude and price sensitivity of demand can be resolved using the early sales information. In this study, a Bayesian model is developed to summarize sales information and pricing history in an efficient way. This model is incorporated into a periodic pricing model to optimize revenues for a given stock of items over a finite horizon. A computational study is carried out in order to find out the circumstances under which learning is most beneficial. The model is extended to allow for replenishments within the season, in order to understand global sourcing decisions made by apparel retailers. Some of the findings are empirically validated using data from U.S. apparel industry. Author Affiliation: (a) Department of Industrial Engineering, Bilkent University, Bilkent, Ankara 06800, Turkey (b) Hewlett Packard Laboratories, 1501 Page Mill Road, MS 1U 2, Palo Alto, CA 94304, USA Article History: Received 11 October 2005; Accepted 5 May 2008

A method for tackling the multiple lot sizing problem in inventory management, by using dynamic programming, is presented.

Numerical results of a periodic-review model for joint demand fulfillment probability in a multi-item inventory system indicated that even if optimal combination order-up-to levels relies on the relation of item demands, a heuristic which disregards the connection is extensively quite effective, given that demand averages and variances are properly accounted for. One advantage of the model is that only the correlations of aggregated item demands in a time is needed, instead of individual orders.

The advance payment scheme is used when a payment larger than the billed amount is made. The extra payment is effectively a cash deposit for credit towards bills in future periods. This study presents a model for determining the optimal cash deposit amount when there is a fixed per-payment cost; the model balances the tradeoff between the fixed payment cost with the lost interest on the cash deposit. We use a renewal theory approach to obtain the long-term expected total cost per period when the bill amounts in a future period are deterministic, exponentially distributed, normally distributed, or Poisson occurrence based with a constant per occurrence charge. For the first two cases, we obtain explicit expressions for the optimal deposit amount; for the latter two, we give numerical procedures. An example in each case is presented, along with a comparison with the usual pay-each-period strategy. We conclude that the advance payment strategy offers significant cost savings when the per-payment cost is relatively large compared with the lost interest of one period's average bill amount; i.e. when interest rate is low or the average bill amount is small. Key words - cost models, deposit policy, inventory theory application

The article presents a model for evaluating product fulfillment rates in an assemble-to-order system with a two-level bill-of-material structure. Many assembly and distribution systems have explicitly stated percentage goals for fulfilling customer orders within a prespecified time. Providing quick and reliable customer order delivery has been an important dimension of competitiveness. Meanwhile, the pressures for maintaining low inventory levels and providing flexibilities to respond to different customer needs have driven many manufacturing systems to operate in an assemble-to-order manner in which only component, rather than product, inventories are kept. In this article, researchers studied the order fulfillment performance of an assembly system consisting of n components from which m products are assembled. The model for evaluating the fulfillment rates explicitly considers product-component structure, component commonality, fulfillment rules, and demand correlations. This model relates various system parameters such as component lead times, order-up-to levels, product demand correlations, and fulfillment windows.