امکان مدیریت ارتباط با مشتری در خدمات ISP از طریق استفاده از الگوهای استخراجی
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|866||2006||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 6857 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
- تولید محتوا با مقالات ISI برای سایت یا وبلاگ شما
- تولید محتوا با مقالات ISI برای کتاب شما
- تولید محتوا با مقالات ISI برای نشریه یا رسانه شما
پیشنهاد می کنیم کیفیت محتوای سایت خود را با استفاده از منابع علمی، افزایش دهید.
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 30, Issue 4, May 2006, Pages 621–632
The monopoly of state ownership of telecommunication industry in Taiwan was lifted in 1997. In choosing an ISP, pricing was and still is a main differentiating factor in the mind of customers; however, service quality has emerged as a major concern among users lately. Management of ISP has discovered that service quality is important not only for attracting new customers, but, more importantly, for retaining existing customers who may otherwise be lured away by lower fees. Hence, it is essential to develop a CRM system, which could help keeping existing customers and exploring further business opportunities at the same time. In this study, we, based on the IP traffic data, developed a CRM systematic approach for a major ISP company in Taiwan to enhance customers' longer-term loyalty. This approach employs CRISP-DM methodology, and applies Attribute-Oriented Induction as the mining technique to discover network usage behaviors of customers, which help management identify usage pattern and also pinpoint the time when usage is excessively heavy. The former allows management to make effective personal calls for services or maintenance, and the latter presents opportunities for management to offer personalized cares and advanced products. Pixel-oriented visualization is applied to improve the understanding of mining results.
The wave of liberalization of global telecommunication industry started in early 1980 s. It resulted in a great number of private ownerships, and the subsequent development of advanced technology in telecommunication and service delivery. Its effects in contributing toward world economy have been very obvious. Following the footsteps of the rest of the world, the telecommunication market in Taiwan was also liberalized in 1997. Since then, there has been several big players entering the market and competing for the services of the first tier, which include fixed telecommunication network, mobile telecommunication network, and satellite communication network. There are also a number of smaller players competing for the services of the second tier and are called ISP (Internet Service Provider), which include mainly the telecommunication value-added services. Among the many services that are offered by ISP industry, the combination of mobile communication and Internet service is becoming the backbone of the present and future m-commerce. The state-of-the-art services offered by mobile services can be classified into four categories: (1) information services, (2) entertainment services, (3) communication services, and (4) transactional services (Adela, 2003). These four categories will enable users to make purchases, request services, access news and information, and pay bills, through mobile communication devices such as PDAs, laptops, and cellular phones. The Internet services that are offered by an ISP company in general include content service domain, access domain, Internet routing domain, authorization and accounting domain, and network management. The fact that ISP industry deals with individual customers directly has led to more intense competition than other sectors of the industry. For an ISP company to become viable in the long run, the number of customer is essential in lowering the cost base. To achieve this end, most companies initially resort to pricing strategy to attract customers. However, after these years, they started to realize that service quality might be more important than small differences in fees; that means companies need to retain existing customers through better services. In a sense, the marketing mode has shifted from being product-oriented to customer-oriented, which fits well with the well accepted principle in marketing that keeping existing customers is more profitable than attracting new customers (Bitran & Mondschein, 1997). As a result, the pressing problem that is confronting ISP management is simply how to understand the service needs of users, and provide them accordingly. The objective of this research is to apply the well-known data mining methodology CRISP-DM to investigate network usage behaviors of ISP subscribers in Taiwan, so that an appropriate CRM strategy may be developed for individual care and/or personalized marketing, which would contribute toward enhancing the long term relationships with existing customers. In particular, we apply Attribute-Oriented Induction (AOI) method (Cai et al., 1991, Han and Kamber, 2001 and Han et al., 1993) for discovering characteristics and discrimination knowledge of ISP customers from the IP traffic data. The AOI method is a useful data mining approach for generalizing and summarizing interesting concepts based an appropriate concept hierarchy. It has been successfully applied to a variety of domains such as mining intrusion detection alarms (Julisch & Dacier, 2002), mining high-level multimedia knowledge (Zaiane, Han, Li, Chee, & Chiang, 1998), and mining Web logs (Fu, Sandhu, & Shih, 2000). The structure of this paper is as follows. In Section 2, we provide the background information of ISP industry in Taiwan. Section 3 describes the methodology used in this research. In Section 4, we present the data-mining model and describe the development process and the mining results, which is followed by Section 5 of conclusions.
نتیجه گیری انگلیسی
This research investigates how ISP industry can apply data mining techniques to discover users' online usage knowledge, and develop strategies to strengthen customers' relationship. We use sampled IP traffic as data, and, following a concept hierarchy, applied Attribute Oriented Induction to generalize concepts for a period of time. Through the selection of two different usage Threshold-Rate, we are able to investigate users' general network usage pattern as well as that of heavy usage over time. The former allows management to make direct and effective person-to-person contacts, and the latter offers opportunities for management to provide VIP class care and presents advanced products. The combined effect will enhance the long-term loyalty of customers. The results of this research present brand new concept to the company where the data was collected, which provide very important information for both service department and sell department to re-align resources of both work force and working hours. This work can be further extended to investigate users' network usage behaviors of one region by segregating users into different groups. A system can then be further developed to integrate various modules mentioned above, so that management will be able to indicate city, suburb, threshold, data collection period, and view users falling into the same group. This can facilitate management to take different actions for different groups.