کاوش در اطلاعات متن برای بهینه سازی مدیریت ارتباط با مشتری (CRM)
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|1003||2009||11 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 6389 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 36, Issue 2, Part 1, March 2009, Pages 1433–1443
Customer data warehouse and mining are able to provide the structure of recording of the whole customers’ information, the flow of detecting the important customers systematically, the change of identifying the individual and valuable customers in the whole name list of customers or discovering the royal customers. Generally speaking, it is no doubt that “customer relationship” is one of the most important factors to construct the core of competitiveness, especial in service industries for running business forever. Therefore, the objective of this research is to apply the data warehouse and data mining technologies to analyze the customers’ behavior in order to form the right of customers’ profile and it growth model under Internet and e-commerce environment. This could provide the best service model owing to the enounced of customer-orientation and making more effective marketing strategy. Consequently, a case study will be presented to verify the feasibility and effectiveness of the approach proposed in this research.
Linoff and Berry (2002) indicate that when managing hundreds of thousands of customers, businesses will have difficulty sustaining the rising costs created by interactions among people. However, if all customer data is inputted into a database, the resulting records will provide a detailed profile of these customers and their interactions with one another, and will be an important resource for businesses that wish to probe customer data, customer needs, and customer satisfaction levels (Aha, Kibler, Albert, & Albert, 1991). Data mining uses transaction data to gain a better understanding of customers and effectively discover hidden knowledge through the insertion of business intelligence into the process of customer relationship management. More precisely speaking, it replaces artificial intelligence, and for this reason the technology has become popular in recent years. Data warehousing, then, is a useful and accurate tool for assembling a business’s dispersed heterogeneous data and providing unified convenient information access technique, because it can process large amounts of information with the support of its unique data storage structure and network architecture. In the business world, once the foundation of a data warehousing system is laid, data mining technology can be used to transform hidden knowledge into manifest knowledge. The results improve the independent decision-making abilities of employees and help businesses attain Gates’s model: Digital activity as the kernel for building business processes and providing timely information to appropriate decision-making units (Gates, 1999). Popularizing information automation has resulted in heavy utilization of information technologies, such as the internet and automated telephone answering systems, construction of dynamic websites, and implementation of ERP and operational CRM systems; their emphases are on process optimization and efficient, highly precise account management. With the increased popularity of personalization management, the integrated CRM aim to seek quality service and high levels of customer satisfaction. An integrated CRM system is extremely flexible – It can adjust customer needs throughout a product’s life cycle, and it has the ability to analyze and actively monitor customer preferences. Therefore, one of the best competitive strategies is the successful utilization of information technology to swiftly and effectively integrate business knowledge and provide the business with timely quality decision support. Today, businesses face the challenges of using the past to predict the future and using past experiences to communicate effectively with the customer. The most common forms of customer interaction are as follows: (1) Face-to-face interaction with retail personnel; (2) Calls to customer service centers and conversations with customer service representatives; (3) Comments on company websites; and (4) Opinions expressed through e-mail. Customer data harvested through these methods is usually unstructured; however, most data mining technologies can only handle structured data, which means that the data warehouse must have explicit field structures. Therefore, during customary data warehousing processes, unstructured data is not taken into account and much valuable customer information is lost. This study uses content analysis to transform unstructured textual content into structured data; the systematic application of the coding principles of content analysis can produce derived variables and objectively quantify unstructured textual content. These construct a more complete customer data platform for data mining analysis and the extraction of hidden individualized knowledge for optimizing marketing strategies.
نتیجه گیری انگلیسی
Using content analysis and the Analysis Services decision analysis tool, this study developed an easily executed model and completed implementation of customer relationship management. The process of implementing this model not only introduces participating personnel to the concepts of customer relationship management, but also provides an actual foundation for building a customer relationship management system. The purpose of this study is to find ways to study text data in order to discover more latent knowledge. In the example of Company A’s customer service center, content analysis was used to process text data, part of the structured data was integrated into a miniature data warehouse, OLAP analysis and decision tree criteria were used to discover customer knowledge, and, finally, marketing strategies of customer relationship management models were suggested based on these criteria. However, in this example, there was not a good information system in place, and the structured data was sparse and overly dispersed. Data mining did not yield any significant discoveries, so the data analysis was indeed cursory. Therefore, the study’s recommendations still focus on the execution process of complete customer relationship management and on establishing a more complete system loop in order to reinforce interactions with customers. The contributions of this study are as follows: i. The categories established by classifying text data can be used in follow-up studies. ii. The process of using content analysis to transform text data into structured data can be used to supplement training of system operation personnel. iii. An implementation model for customer relationship management was established; the model is particularly useful for smaller businesses that have incomplete information systems. 5.1. Recommendations for Company A The recommendations for Company A are divided into three categories as follows: i. Management of text Data – The study’s empirical process revealed that not only is content analysis useful in organizing and analyzing text data, its reliability testing methods can also be used in future education and training for customer service systems. When training new personnel, after explaining the classification of current customer service data, reliability can immediately be tested. If the reliability is acceptable, it indicates that the new personnel have obtained sufficient understanding of the customer service process; if, after many tests, the reliability is still not up to standards, it indicates that there is a discrepancy between the new personnel’s and the current personnel’s understandings of the current classes. The latter can mean two things: The new personnel do not have sufficient understanding of the customer service process and are unsuitable for data classification tasks; or, some customer data are currently difficult to classify, and the system’s current customer data classes need to be examined and modified if necessary. ii. Analysis of Complaints – Company A currently still relies mainly on strategy groups to promote its business. If the current corporate-level customers have complaints, they usually contact the unit with which they are working. Therefore, although handling of complaints is usually the main task of customer service centers, data analysis indicates that this is not the case for Company A. Thus the role played by its customer service center is not complaint management but more along the lines of business promotion, such as providing progress updates, related data, and potential technological cooperation on the development of new technology, etc. Unless Company A plans to promote its own products, the customer service center’s main responsibility should still be that of handling normal complaints. iii. Operating Model of the Customer Service System – The data is overly dispersed on Company A’s website and it is difficult to perform searches. This is made evident by the analysis of the overall business, where it is clear that its main needs are informational. This is precisely the task that the customer service center can easily handle. Therefore, the establishment of a system for searching online publications should be a priority task in digital marketing. During the beginning construction stages, the customer service center can beta-test the system internally; after beta testing is completed, the system can be unveiled to customers. This system can be used to recruit new members and systematically collect customer data by classifying according to membership and whether payment is collected, remedying the current deficiency of insufficient basic customer data. The system can also be integrated with the electric news system, allowing the customers themselves to choose whether to subscribe to electric news and the types of electric news to which they subscribe. This provides customer classification, and the electric news can actively market publications to various customer groups. Currently, the electric news carries information about conference activities, but do not contain information about conference attendance and revenue, proving that one-way communication of information is unsatisfactory. The necessity of reporting conference activities can be examined from the perspective of creating repeated interactions between the company and its customers. If the online conference registration system or related online surveys can be further integrated, creating a two-way communication channel, in addition to enhancing online reporting of conference information or content, additional customers can be attracted to the conferences. The integrated system can now actively reach out to conference attendees, and an expanded customer base will result in increased subscriptions to electric news and more effective digital marketing. This establishes the beneficial cycle of customer relationship management as seen in Fig. 6.