نقش عوامل هوشمند و داده کاوی در مدیریت مشارکت الکترونیکی
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|3605||2012||12 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 7808 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
|شرح||تعرفه ترجمه||زمان تحویل||جمع هزینه|
|ترجمه تخصصی - سرعت عادی||هر کلمه 90 تومان||12 روز بعد از پرداخت||702,720 تومان|
|ترجمه تخصصی - سرعت فوری||هر کلمه 180 تومان||6 روز بعد از پرداخت||1,405,440 تومان|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 39, Issue 18, 15 December 2012, Pages 13277–13288
The marketspaces of the “New Economy” and the eServices revolution have enabled the formation of new types of partnerships which are electronically mediated. Web-based electronic commerce has also brought a tremendous increase in the volume of data that can be mined for valuable managerial knowledge. The data mining procedures used in this process can be enhanced by employing intelligent agents. This paper describes emerging electronic partnerships between players in developing electronic marketspaces and identifies typical data flows between such players, with an analysis of the potential role of data mining and intelligent agent technology. By identifying the complex nature of information flows between the vast numbers of economic entities, we identify opportunities for applying data mining techniques that can lead to knowledge discovery. In particular, we show how a Generic Agent-based data Mining Architecture (GAMA) can be customized to support managerial decision-making and problem solving in a networked economy. A prototype implementation of GAMA is presented, along with a demonstration of the some of the capabilities of the system. Finally, we explore the role of agents in promoting and maintaining strong automated relationships between various strategic partners.
Millions of individuals surf the Web every day and interact with electronic commerce Websites around the world. While many sites capture user activity, most do not capture all interactions with “etail” (electronic retail) consumers, suppliers, and partners, and they do not maximize the potential uses for such data (Liu et al., 2011 and Willow, 2005). According to Forrester Research, only 18% of the companies it surveyed use their Web data for marketing purposes, and only 16% use it for customer support. The Forrester study also indicates that 72% of the companies that collect Web data admit that they do not analyze this data or use it in any application. However, organizations are beginning to realize the value of this Web data and are allocating vast resources for creating the necessary infrastructure to analyze this data, which would enable them to learn more about their customers and gain a competitive advantage (Rajan and Saravanan, 2008, Yarom et al., 2003 and Zuo and Hua, 2012). The sheer volume of data generated by the activities of visitors to a company’s site (their “digital footprint”) poses various problems in the storage, management, and analysis of this data as well as new opportunities. Some companies rush to set up their electronic storefronts, focusing more on transaction processing, online inventory, shopping carts, and ad banners, without giving sufficient consideration to the data management issues (Gomes and Canuto, 2006 and Holmes et al., 2012). In order to get the most mileage out of this data, each company must decide: (a) what data to collect and how to organize it; (b) what kind of analysis to perform on the data; (c) how frequently to perform data analysis; and (d) how to validate and integrate the results into decision making and planning. As data warehousing and data mining technologies mature, an increasing number of organizations are employing these technologies in their problem solving and managerial decision making in the business to consumer context (Rao, 2010). Through data mining, a company can synthesize consumer Website patterns into meaningful information, enabling it to understand and engage customers and prospects over the Internet (Chaimontree et al., 2012 and Nassiri, 2009). The mining of Web-based data and the implementation of the business intelligence it represents is the key to creating a lasting relationship with online customers and establishing a successful online storefront. But in the future, mining the Web service interactions between company Websites will also enable them to create lasting relationships with their strategic partners (Jain, 2012 and Marik and McFarlane, 2005). There are several commercial software products available to analyze Web traffic data such as NetTracker, WebTrends, NetIntellect, HitList, and SurfReport. However, these products are limited to analyzing server activity based on the data stored in log files. By unifying the log data with personal information supplied by vendors such as Equifax, Experian, TransUnion, MetroMail, and others, one can develop a more complete customer profile. This integrated information can then be mined to gain insight into who is buying what products, what products are the most popular, buying patterns, and so forth (Gao et al., 2012, Jayabrabu et al., 2012 and Kehagias and Mitkas, 2007). The dynamic nature of the online environment dictates that this analysis should be performed promptly to enable companies to quickly respond to changes in customers’ buying behavior. There are myriad data mining tools available in the market that employ a variety of data mining algorithms and techniques. For a novice user, it is often difficult to determine which tools or techniques are appropriate for a particular data analysis or data mining scenario. Companies are beginning to employ “intelligent agents” (Chan et al., 1999, Gannon and Bragger, 1998, Gorodetsky et al., 2008, Grimes, 1998 and Sugumaran and Bose, 1999) to reduce some of this cognitive load. These agents can automate some of the mundane activities such as data cleansing and data transformation and can help the user in the selection of appropriate tools and data mining methods (Li and Li, 2011, Lee and Liu, 2004 and Moemeng et al., 2010). Typically, intelligent agents act on behalf of the human user in problem solving activities and decision making. The objective of this research is to: (a) study the information flow between various entities in different electronic markets; (b) investigate how data warehousing and data mining techniques can be applied for discovering new relationships and nuggets of knowledge that could be incorporated into managerial decision making; and (c) develop a generic architecture for an intelligent-agent based data mining environment; and (d) apply this architecture to various eCommerce marketspaces to help the user validate and interpret the results, thereby enabling the discovery of valuable knowledge. The remainder of this paper is organized as follows. The next section (“Emerging eCommerce Marketspaces and Data Flows”) presents a vision of relationships between strategic partners facilitated by the implementation of interoperable automated processes. The following section (“Relationship Management in the New Economy”) focuses on collaborative commerce (cCommerce) activities such as outsourcing and establishing strategic partnerships through the use of intelligent agents. The next section (“Emerging Technologies”) provides an overview of emerging technologies such as data warehousing, data mining, and intelligent agents, and shows some examples of their use on the Web. The following section (“Generic Architecture for Agent-Based Data Mining”) proposes an architecture for a generic agent-based data mining environment. This Generic Agent-Based Data Mining Architecture (GAMA) can be customized to support managerial decision-making and problem solving for a particular application. The penultimate section (“Agent-based Data Mining Applications in eCommerce”) provides a detailed discussion of the application of intelligent agent-based data mining in different electronic marketspaces such as etailing and B2B exchanges. The final section (“Managerial Implications and Future Directions”) concludes the paper by discussing the issues in agent-based data mining and their managerial implications.
نتیجه گیری انگلیسی
Many companies in both B2C and B2B markets are implementing agent-based data mining technologies. Firms using data mining processes within these eCommerce marketspaces should consider some key managerial implications. Success will be determined by the way these tools are used, not by the tools themselves. First, many firms have not yet effectively implemented data mining technology and are failing to collect valuable data every day. This valuable data, which leads to an understanding of a company’s market, may make the difference between long-term success and failure in these competitive marketspaces. Data mining techniques provide important tools for personalizing a customer’s shopping experience and creating customer intimacy in an online experience. Managers of eCommerce sites must develop and use agent-based data mining to maximize their chance of success in these marketspaces. Managers must also develop realistic business rules for evaluating and interpreting data mining results. These business rules will be unique to each company’s value proposition and customer base. After interpreting the results, managers must implement such information effectively. Many data mining efforts have incorporated state-of-the-art methods but have not led to success due to poor implementation protocols. It is imperative that managers organize the results of the knowledge discovery process so that the exercise leads to appropriate managerial responses. Consumer privacy is another important managerial issue for companies pursuing agent-based data mining. The large amount of clickdata which identifies patterns of usage by individual customers can be combined with personally identifiable information (such as name, address, and telephone number) to generate profiles, creating significant opportunity for abuse (Harmon et al., 2009 and Junnarkar, 2000). In order to ensure that agents maximize their ability to gather valuable data for mining into managerial knowledge, it is imperative that the players in these electronic marketspaces adopt XML-based standards for representing attributes and attribute values of their products, services, sales, customers, and policies (Warkentin, Sugumaran, & Bapna, 2001a). Interorganizational systems cannot have a significant impact unless a standard data representation scheme is used for data of mutual value. The true potential of intelligent agents to efficiently exchange information will not be unlocked unless and until there is a common standard for the representation of all product and service attributes which can be easily transferred and interpreted by all economic players across the Internet. An international standardized data representation scheme for product and service attributes would extend the capabilities of agent-based data mining processes, thus further improving the efficiency of all marketspaces throughout the World Wide Web. The emergence of data mining and intelligent agents at the same time that millions of individuals have gone online to purchase from thousands of new Websites has created an exciting opportunity for practical technological convergence. As eCommerce moves many business processes and activities online, new data streams are born and a chance for greater efficiencies is generated for those willing to carefully perform the correct data analysis procedures. Agent-based data mining will enable firms to capture the full potential of this technological convergence.