• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.4
• /
• pp.71-81
• /
• 2005

This Paper focuses on the effects of outside competition on an optimal echelon base stock level in a two stage supply chain. This is new in that we have been studying the effects of inside competition within a supply chain up to now. It is known that the optimal echelon base stock level with inside competition within a supply chain is less than the global optimal echelon base stock level without inside competition. This is due to the ' public goods ' nature of inventory. That is, more inventory is better, but one wants the other to invest more, thus resulting in under-investment. However, this phenomenon becomes weaker as outside competition increases. We show that as outside competition becomes stronger, the ' public goods ' effects decrease and the optimal echelon base stock level increases. If the level of competition is sufficiently high, the optimal echelon base stock level goes even higher than the global optimal echelon base stock level. We develop a theoretical model for the analysis and conduct a numerical analysis.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.30 no.3
• /
• pp.89-93
• /
• 2007

In this study, we consider an assembly line operated under a base-stock policy. A product consists of two parts, and a finished product transfers to a warehouse in which demands are satisfied. Assume that demands arrive according to a Poisson process and processing times at each production line are exponentially distributed. Whenever a demand arrives, it is satisfied immediately from an inventory in the warehouse if available; otherwise, it is backlogged and satisfied later by the next product exiting from production lines. In either case, an arriving demand automatically triggers the production of a part at both production lines. These two parts will be assembled into a product that eventually transfers to the warehouse. We obtain a closed form formula of approximation for delay time or lead time distribution of a demand when a base- stock level is s. Moreover, it can be applied to the optimal base-stock level which minimizes the total inventory cost. Numerical examples are presented to show our optimal base-stock level's quality.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.132-139
• /
• 2019

We address the problem about forecasting the direction of stock price movement in the Korea market. Recently, the deep neural network is popularly applied in this area of research. In deep neural network systems, proper parameter initialization reduces training time and improves the performance of the model. Therefore, in our study, we propose a novel parameter initialization technique and apply this technique for the stock price movement prediction model. Specifically, we design a framework which consists of two models: a base model and a main prediction model. The base model constructed with LSTM is trained by using the large data which is generated by a large amount of the stock data to achieve optimal parameters. The main prediction model with the same architecture as the base model uses the optimal parameter initialization. Thus, the main prediction model is trained by only using the data of the given stock. Moreover, the stock price movements can be affected by other related information in the stock market. For this reason, we conducted our research with two types of inputs. The first type is the stock features, and the second type is a combination of the stock features and the Korea Composite Stock Price Index (KOSPI) features. Empirical results conducted on the top five stocks in the KOSPI list in terms of market capitalization indicate that our approaches achieve better predictive accuracy and F1-score comparing to other baseline models.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.32 no.1
• /
• pp.93-104
• /
• 2007

We consider a supply chain where products are shipped to warehouse from manufacturing system to customers. Products are supplied from either in-house regular manufacturing or the secondary source such as subcontractor. The inventory in warehouse is controlled by base-stock policy, that is, whenever a demand arrives from customer, an order is released to the manufacturing system. Unsatisfied demand is backlogged. The manufacturing system is modeled as M/M/s+1/c queueing system, and the orders exceeding the given limit care blocked and lost. The steady state distribution of the outstanding orders and the throughput of the manufacturing system are functions of the level of engagement In the secondary source. There is a profit obtained from throughput and cost not only due to the engagement of the secondary source in the manufacturing system but also inventory positions. We want to maximize the total production profit minus the total cost of the production system by simultaneously determining the optimal level of engagement of the secondary source and the optimal base-stock level of the inventory. We develop two algorithms : one without guarantee of the optimal solution but with the small number of computations, the other optimal but with more computations.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2008.10a
• /
• pp.267-284
• /
• 2008

Consider a supply chain where products are produced at a manufacturing system, shipped to a distribution center, and then supplied to customers. The distribution center controls inventory based on a base-stock policy, and whenever a unit of product is demanded by a customer, an order is released to the production system. Unsatisfied demand is backordered, and the inventory and backordered units are a function of the base-stock level. The manufacturing system is modeled as an M/M/s/c queueing system, and orders exceeding the limited buffer capacity are blocked and lost. The throughput of the manufacturing system and the steady state distribution of the outstanding orders are functions of number of servers and buffers of the manufacturing system. There is a profit obtained from throughput and costs due to servers and buffers of the manufacturing system, and also costs due to inventory positions of the distribution center, and we want to maximize the total production profit minus the total cost of the supply chain by simultaneously determining the optimal number of servers and buffers of the manufacturing system and the optimal base-stock level of the distribution center. We develope two algorithms, one analytical but without guarantee of the optimal solution and one optimal but without complete analytical proofs. The problem integrates strategic problem of the manufacturing system with tactical problem of the distribution center in a supply chain.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.31 no.1
• /
• pp.105-115
• /
• 2006

In this paper, we investigate the problem of minimizing average inventory costs subject to a fill rate constraint in a two-stage serial inventory model with a normally distributed demand. Fill rate is the fraction of demand that is satisfied immediately from on-hand inventory. We first find the lower bounds of base-stock levels in each node by using the exact base-stock level that satisfies a fill rate in a single node model proposed by Sobel. And then, we extensively analyze the system and show that the cost function is convex. Using such convexity and some other useful properties, we can easily find optimal base-stock levels numerically.

• The Journal of Fisheries Business Administration
• /
• v.23 no.2
• /
• pp.53-67
• /
• 1992

It has been recognized, virtually from the time of its inception, that fisheries economics, like other aspects of resource economics, should ideally be cast in capital-theoretic terms. The fish population or biomass can be viewed as a capital stock in that, like conventional or man-made capital, it is capable of yielding a sustainable consumption flow through time. This study is to introduce the optimal control theory which was extended from the theory of calculus of variations into the study of former static theory of fisheries economics started by Gordon (1954). The optimal control theory eliminated the inadequacies of the classical techniques to a large extent. From this point of view, this study, on the base of Schaefer model, summerizes most of major results achieved so far, but does so in a manner such that the links with capital theory are made transparent. This study explores two sets of problems. The first concerns the optimal approach to the equilibrium stock, i.e. the optimal investment policy. The second set of problems arises from the relaxation of the highly restrictive assumption of autonomy (i.e. the assumption that the parameters are independent of time), then concludes the relaxation of linearity assumption together with the complexities caused by that.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.10
• /
• pp.58-67
• /
• 1997

Generally, die polishing process occupies about 30 .approx. 50% of the whole die manufacturing time. However, die polshing has not been automated yet, since it needs a great deal of experience and skill. This study aims at development of an expert system for die polishing which gives such optimal parameters as tool and polishing conditions. Through experiments, polishing characteristics such as surface roughness, stock removal and scratch were analyzed quantitatively for each polishing tool, and a knowledge base for the expert system was established. Evaluation tests show that the developed system works well to suggest the optimal polishing conditions and it is very promising.

• Journal of the Korea Safety Management & Science
• /
• v.16 no.4
• /
• pp.323-330
• /
• 2014

Various inventory control theories have tried to modelling and analyzing supply chains by using quantitative methods and characterization of optimal control policies. However, despite of various efforts in this research filed, the existing models cannot afford to be applied to the realistic problems. The most unrealistic assumption for these models is customer demand. Most of previous researches assume that the customer demand is stationary with a known distribution, whereas, in reality, the customer demand is not known a priori and changes over time. In this paper, we propose a reinforcement learning based adaptive echelon base-stock inventory control policy for a multi-stage, serial supply chain with non-stationary customer demand under the service level constraint. Using various simulation experiments, we prove that the proposed inventory control policy can meet the target service level quite well under various experimental environments.

• IE interfaces
• /
• v.22 no.4
• /
• pp.368-375
• /
• 2009

This paper considers a two-stage supply system consisting of two make-to-stock facilities. The facility in the first stage produces a single type of component in anticipation of future demands from the market and the end item production while the facility in the second stage produces the end item in anticipation of future demands from the OEM customers. The facility in the first stage has the option of to accept or reject each incoming demand from the market. In this paper, we address the problem of how to control the exogenous component demand and how to manage the production of the end item and the component so as to maximize the system's profit subject to the system costs. In this paper, we present a heuristic policy that is the base-stock production policy combined with a linear switching curve for component demand control. Numerical study is implemented under different operating conditions of the system and it shows that the performance of the heuristic is very promising compared to that of the optimal policy for the Markov model.