Designing of an intelligent self-adaptive model for supply chain ordering management system

Mortazavi, Ahmad; Khamseh, Alireza Arshadi; Azimi, Parham

doi:10.1016/j.engappai.2014.09.004

Cited by 68 publications

(36 citation statements)

References 28 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several works propose machine learning-based frameworks for managing the inventory at all nodes of the supply chain in a coordinated manner, such as Giannoccaro and Pontrandolfo (2002), Chaharsooghi, Heydari, and Zegordi (2008), and Mortazavi, Khamseh, and Azimi (2015). Their solutions employ different algorithms for reinforcement learning, e.g.…”

mentioning

confidence: 99%

Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

Priore

Ponte

Rosillo

et al. 2018

International Journal of Production Research

119

View full text Add to dashboard Cite

show abstract

mentioning

confidence: 99%

Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

Priore

Ponte

Rosillo

et al. 2018

International Journal of Production Research

119

View full text Add to dashboard Cite

show abstract

“…Developments in artificial intelligence (AI) for some aspects of tertiary care center management is predicted to lower costs. These may include machine learning algorithms in medical billing, supply chain management, scheduling efficiencies, virtual radiology (for image interpretation), and prevention of readmissions [71][72][73][74][75][76][77].…”

Section: Information Technology and Quality Benchmarksmentioning

confidence: 99%

Worldwide Network for Blood and Marrow Transplantation Recommendations for Establishing a Hematopoietic Stem Cell Transplantation Program in Countries with Limited Resources, Part II: Clinical, Technical, and Socioeconomic Considerations

Aljurf

Weisdorf

Hashmi

et al. 2019

Biology of Blood and Marrow Transplantation

View full text Add to dashboard Cite

A B S T R A C T The development of hematopoietic stem cell transplantation (HSCT) programs can face significant challenges in most developing countries because such endeavors must compete with other government health care priorities, including the delivery of basic services. Although this is may be a limiting factor, these countries should prioritize development of the needed expertise to offer state-of-the-art treatments, including transplantation, by providing financial, technological, legal, ethical, and other needed support. This would prove beneficial in providing successful programs customized to the needs of their population and potentially provide long-term cost savings by circumventing the need for their citizens to seek care abroad. The costs of establishing an HSCT program and the costs of the HSCT procedure itself can be substantial barriers in developing countries. In addition, socioeconomic factors intrinsic to specific countries can influence access to HSCT, patient eligibility for HSCT, and timely utilization of HSCT center capabilities. This report describes recommendations from the Worldwide Network for Blood and Marrow Transplantation for establishing HSCT programs, with a specific focus on developing countries, and identifies challenges and opportunities for providing this specialized procedure in resource-constrained settings.

show abstract

“…Kim et al [25] presented a multi-agent framework -considering a reward function-for an inventory management problem with the uncertain demand and the service level constraint. In the recent years, some papers applied reinforcement learning on the multi-agent simulation framework: [26], [27], [28]. As clarified in the previous sections and to the best of our knowledge, there is no research in the literature which modeled a multi-period newsvendor problem with many to many relationships and uncertain capacitated suppliers.…”

Section: Literature Reviewmentioning

confidence: 99%

Simulation based optimization of a stochastic supply chain considering supplier disruption: An agent-based modeling and reinforcement learning

Aghaie

Heidary

2018

Scientia Iranica

View full text Add to dashboard Cite

Many researchers and practitioners in the recent years have been attracted to investigate the role of uncertainties in the supply chain management concept. In this paper a multi-period stochastic supply chain with demand uncertainty and supplier disruption is modeled. In the model, two types of retailers including risk sensitive and risk neutral, with many capacitated suppliers are considered. Autonomous retailers have three choices to satisfy demands: ordering from primary suppliers, reserved suppliers and spot market. The goal is to find the best behavior of the risk sensitive retailer, regarding the forward and option contracts, during several contract periods based on the profit function. Hence, an agent-based simulation approach has been developed to simulate the supply chain and transactions between retailers and unreliable suppliers. In addition, a Q-learning approach (as a method of reinforcement learning) has been developed to optimize the simulation procedure. Furthermore, different configurations for simulation procedure are analyzed. The R-netlogo package is used to implement the algorithm. Also a numerical example has been solved using the proposed simulation-optimization approach. Several sensitivity analyzes are conducted regarding different parameters of the model. Comparison of the numerical results with a genetic algorithm shows a significant efficiency of the proposed Q-leaning approach.Keywords Supply chain management, simulation based optimization, reinforcement learning, demand uncertainty, supplier disruption. IntroductionThe Importance of uncertainties and consequent costs of ignoring them, caused a shift from deterministic configurations of the supply chain to the stochastic models. One of the most important problems in the stochastic supply chain ordering management is the newsvendor (NV) problem. The basic form of the NV problem consists of a buyer and a seller in which the buyer must decide on the amount of ordering from the seller while demand of the customers is not predetermined. In the basic form, the buyer only has an overall information about the customer demand such as the distribution function. Also the decision is made only at one period. The objective is to optimize the profit of the buyer. Two extensions of the problem have been done by the researchers: the multi-period NV Problem (MNVP), the NV Problem with Supplier Disruption (NVPSD). In the MNVP, the buyer(s) decides on the amount of ordering from the seller(s) at the beginning of each period. The buyer(s) decides on the amount of orders based on the uncertain demands of its customers and the inventory remained from the previous period. In the NVPSD (which is often consisted of one period) the buyer(s) decides on the amount of orders based on the uncertain customer demand and remained fixed capacities of the sellers. In the related literature of the NVPSD it is usually assumed that the network consists of many uncertain sellers and one buyer (e.g. [1], [2], [3]). On the other hand, in the literature of the MNVP, ...

show abstract

Designing of an intelligent self-adaptive model for supply chain ordering management system

Cited by 68 publications

References 28 publications

Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

Worldwide Network for Blood and Marrow Transplantation Recommendations for Establishing a Hematopoietic Stem Cell Transplantation Program in Countries with Limited Resources, Part II: Clinical, Technical, and Socioeconomic Considerations

Simulation based optimization of a stochastic supply chain considering supplier disruption: An agent-based modeling and reinforcement learning

Contact Info

Product

Resources

About