مدیریت کالا مبتنی بر عامل در تجارت الکترونیک B to B
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|3399||2003||23 صفحه PDF||سفارش دهید||10400 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Decision Support Systems, Volume 35, Issue 3, June 2003, Pages 311–333
Currently, there is cutthroat competition in the retail industry, and retail companies struggle for survival. Merchandise management—selecting desirable merchandise, disposing of slow-selling goods and ordering and distributing them—is important to a retailer's success because merchandise is the basis of retailing. Particularly because in an Electronic Commerce (EC) environment, customer preferences are very diverse and their merchant loyalty level is very low, companies should acknowledge the changes in customer demand patterns quickly and respond to them appropriately. However, until now, most retailers have depended on humans for merchandise management. Because there are too many merchandise and brands, it is impossible for merchandise managers to evaluate, compare, select and dispose of merchandise effectively. Retailers need a system that can perform merchandise managers' jobs autonomously, continuously and efficiently. In this paper, we propose an agent-based system for merchandise management, which performs evaluating and selecting merchandise and predicting seasons and building purchase schedules autonomously in place of human merchandise managers under a Business-to-Business (B2B) EC environment. In order to facilitate the agent's intelligent behavior, several analysis tools such as Data Envelopment Analysis (DEA), Genetic Algorithm (GA), Linear Regression and Rule Induction Algorithm are incorporated into the system. Lastly, the proposed system is verified in its application to a duty-free shop.The proposed system would accomplish merchandise management timely, autonomously and efficiently, and the effective merchandise management would reduce the inventory level while increasing sales and profits. The agent-based merchandise management system will enhance a retail company's potential for success. Moreover, it will be necessary for survival in the B2B EC.
The major activities of merchandise management, including selecting, ordering and distributing merchandise, are important to a retailer's success because merchandise is the basis of retailing. Especially, retailers should select popular merchandise and dispose of unpopular ones. Though there have been a lot of systems supporting the replenishment of merchandise, selecting goods have been carried out by human beings in most retail companies. Retailers need a new system that can undertake merchandise managers' jobs—evaluating and selecting merchandise and searching for new, popular merchandise, and accomplishing those tasks autonomously. Moreover, the automation of those tasks will be an indispensable condition for retailers to survive in the Electronic Commerce (EC) environment, in which transactions are growing very rapidly with a great increase of Internet usage, because customer demand patterns change quickly. Because in the EC environment, customer preferences are very diverse and their merchant loyalty level is very low, companies should acknowledge the changes of the patterns quickly and respond to them appropriately. Currently, however, merchandise management, including evaluating, selecting and ordering, is almost entirely driven by human beings, and it will not be possible for retailers to cope effectively with the dynamic changes of customer demand patterns in the EC environment without intelligent and autonomous merchandise management systems. The automation of tasks can be realized by intelligent software agents because autonomy is the most important property of intelligent software agents, and the concept of the intelligent software agent is useful for developing a software system, especially for solving difficult, time-consuming problems. Moreover, in a virtual marketplace in the Business-to-Business (B2B) EC, buying and selling of products between companies are carried out by autonomous agents, and, therefore, other related tasks of retailers such as evaluating, selecting, and ordering merchandise also need to be placed in the hands of intelligent agents for a successful operation of the whole process of retailing. We will propose an agent-based system for merchandise management under the B2B EC environment, which performs the functions of evaluating and selecting merchandise and building schedules for tasks. For that purpose, this research achieves the following objectives. 1.To analyze and configure processes of merchandise management. 2. To design and develop an agent-based system for merchandise management and the architecture and the knowledge of each agent in the system. The proposed system will perform merchandise management autonomously and continuously in place of a human merchandise manager. In order to facilitate the agent's intelligent behavior, several tools such as Data Envelopment Analysis (DEA), Genetic Algorithm (GA), Linear Regression and Rule Induction Algorithm are incorporated into the system. This paper consists of five sections. Section 1 introduces background, motivation and objectives of this research. Section 2 explains previous works related to merchandise management systems and supply chain management. Section 3 describes the components of the proposed system and the architecture and functions of agents. Section 4 shows an application of the system using data from a real retail company. In Section 5, we conclude with limitations of this study and further works.
نتیجه گیری انگلیسی
Merchandise management of retail companies includes selecting desirable merchandise, disposing of slow-selling ones, finding the best supplier who can supply the chosen merchandise and negotiating with them about purchasing and making an order. Until recently, most retailers have depended on human beings for merchandise management, and, thus, retailers have employed many merchandise managers for that purpose. Nevertheless, it has been impossible for merchandise managers to evaluate and compare all of the merchandise, to find appropriate suppliers, to negotiate with them and to order efficiently. Today, however, the tasks can be taken over by intelligent software agents and, moreover, in the agent-based virtual marketplace under B2B EC, merchandise management should be in charge of agents for retailers to respond quickly to the dynamic change of customer need and interact with suppliers efficiently. The proposed agent-based system performs merchandise management autonomously and continuously. It evaluates the desirability of merchandise and selects more desirable goods. It also predicts the desirability of new merchandise. After evaluating and selecting, the system builds schedules for replenishment, selecting suppliers and negotiating. The results of this research can be summarized as following. (1) Autonomous merchandise management by an agent-based system. • Predicting high-demand seasons autonomously: The system segments sales records according to sales patterns and finds high-demand seasons of every merchandise using Genetic Algorithm and Linear Regression. In addition, the system forecasts customer demand and builds replenishment schedules based on the predicted high-demand season. • Evaluating and selecting merchandise autonomously: The system evaluates merchandise soon after every high-demand season and selects merchandise for selling in the next high-demand season. • Predicting the desirability of new merchandise autonomously: The system predicts the desirability of new merchandise based on the knowledge of merchandise classification, which is updated autonomously by agents in the system whenever it is necessary. • Building schedules of purchasing autonomously: The system builds schedules of purchasing such as replenishment schedules and supplier-selecting schedules. (2) Incorporating analysis tools into knowledge of intelligent software agents: In this paper, several analysis tools such as GA, DEA and C5.0 were used in order to enhance the intelligence of software agents, and it was proven to be very effective. Merchandise management by intelligent software agents will be important in B2B EC because intelligent software agents should accomplish most transactions such as selecting suppliers, negotiating, etc., which until now have been performed by human beings. Hence, the significance of this research is that it is a new trial of developing intelligent software agents for the retail industry, especially for merchandise management in B2B EC. In B2B EC, retail companies can also utilize intelligent software agents for selecting suppliers, purchase negotiating and searching merchandise, which are the tasks of external agents, as explained in Section 3. For that purpose, however, significant related research such as a standard protocol for communication between agents and standard merchandise code structures should be performed. This is our future research.