Summary of the Article
The article under consideration, written by Chye and Gerry (2002), focuses on data mining as a part of newly emerging tools for the business assessment processes. The authors state that data warehousing and knowledge management are other components of new information systems (Chye & Gerry, 2002). According to the article, data mining aims to identify “valid, novel, potentially useful, and understandable correlations and patterns in data” (Chye & Gerry, 2002, p. 1). It could be stated with certainty that the advancement of computer technologies, both in terms of hardware and data mining software improvements, significantly facilitates the accessibility and affordability of data mining for different business companies (Chye & Gerry, 2002). The article is subdivided into five parts, which explore various aspects of data mining in the context of customer relationship management. This paper aims to summarize each of the article’s sections subsequently.
Customer Relationship Management
First of all, the article generally elaborates on the notion of customer relationship management (CRM), which is defined as “the process of predicting customer behavior and selecting actions to influence that behavior to benefit the company” (Chye & Gerry, 2002, p. 2). Further, the article states that there are several main objectives of CRM. The first objective is to get closer to the customer by utilizing the data from the enterprise databases (Chye & Gerry, 2002). Thus, a company can predict the customer’s behavior in advance (Chye & Gerry, 2002). Secondly, it is essential for companies to become more customer-oriented. This goal is reached by a greater focus on customer profitability rather than line profitability (Chye & Gerry, 2002). Other objectives include better customer response and loyalty, more efficient lead management, and increased cross-selling possibilities.
Data Mining Methodology
According to the authors, data mining is a relatively recent practice in the business sphere since it emerged in 1994 (Chye & Gerry, 2002). There are five primary stages of data mining: sampling, exploring, modifying, modeling, and assessing the gathered data (Chye & Gerry, 2002). Sampling is required when data is too voluminous or it is needed to avoid problems of generalization (Chye & Gerry, 2002). Exploration and modification stages refer to the processes of understanding the information and developing meaningful insights. In the modeling stage, the actual analysis is performed through a set of different approaches, such as traditional statistical methods, neural networks, decision trees, etc. (Chye & Gerry, 2002). It should be stated that data mining tools are considerably variable and numerous, and thus they are traditionally categorized into three groups according to their purpose: “description and visualisation, association and clustering, classification and estimation” (Chye & Gerry, 2002, p. 4). Overall, the implementation of data mining gives the company a competitive advantage.
Banking Applications
There is a considerable amount of academic literature and research dedicated to the use of data mining in business. For example, the authors state that, according to the professional and trading literature, numerous companies use data mining to be more competitive in their industries (Chye & Gerry, 2002). Considering the application of data mining to banking, it is possible to mention several examples. Firstly, data mining could be used by banks as a part of their risk management, namely operating the credit risks (Chye & Gerry, 2002). Another sphere where this approach is used is customer acquisition (Chye & Gerry, 2002). The employment of enterprise databases makes it possible to predict the customer’s response to the bank’s marketing campaigns.
Application to Churn Modelling
One of the most evident examples of using the data mining methodology is its application to churn modeling. The authors propose a fictional situation where it is needed to consider a customer relation application (or churn modeling) for a fictitious banking company, ZBANK (Chye & Gerry, 2002). ZBANK faces increasing competition on the market due to customer defections (Chye & Gerry, 2002). Through the process of implementing various data mining tools, it is identified that the decision tree model is capable of predicting the number of customers who are inclined to the voluntary churn (Chye & Gerry, 2002). Overall, it should be stated that data mining, with the employment of demographic and transactional information, can accurately identify churners and non-churners.
Data Mining Limitations
Considering the limitations of this approach, it is possible to mention three primary aspects. Firstly, the authors state that some products of random fluctuations will certainly emerge during efficient exhaustive mining of data (Chye & Gerry, 2002). This limitation is particularly true in the context of big data set with different variables. Secondly, the data mining method is well-designed for modeling, but it does not show the same efficiency with the assessment of the results (Chye & Gerry, 2002). Finally, the application of data mining tools requires both profound pieces of knowledge of the sphere to which the method is applied and proficiency in data mining (Chye & Gerry, 2002).
Critiques for the Paper
It should be noted that the article is of considerably high academic quality. It provides a profound overview of data mining methodology in the context of customer relationship management. The article is highly applicable to various spheres of business, and thus it would be useful for a wide range of businessmen and managers. One of the primary strengths of the article is that the authors provide a vast amount of information about data mining, supporting their claims with the evidence from academic literature and real-life examples of banks, which successfully employ the methodology. Among the weaknesses of the article, one can identify that it is primarily focused on banking applications, while other industries are not given enough insights on the implementation of data mining.
Recommendations for More Valuable Research
Further, regarding possible recommendations for the development of more valuable research, one can state that the article’s primary weakness, which is mentioned in the previous section, should be the main reference point for new research. Particularly, it means that the authors should focus more on the applications for other business spheres. It would bring additional value to the paper. Also, since the authors are primarily focused on the banking industry, it would be considered beneficial to add an application of data mining methodology to a real-life banking situation rather than a fictional one.
Further Additions to the Paper
Considering future work that I may add to the paper, I should state that it will be a significant improvement for the paper if a more profound literature review is given. As it was already mentioned, the authors employed a considerably vast number of sources; however, they did not provide specific information on the topics of customer relationship management and risk management. In my opinion, these two aspects of managerial work are immensely important for any company, especially in the banking industry since various risks are involved.
Other Academic Sources on the Topic
Also, it is essential to mention two academic sources, which explore the topics related to the scope of the research under consideration. The first source is an article, written by Khodakarami and Chan (2014). It is chosen because it explores the topic of customer relationship management more profoundly, and it also gives profound insights on the employment of data mining tools in CRM. The second article by Chen, Deng, Wan, Zhang, Vasilakos and Rong (2015) investigates the peculiarities of the implementation of data mining methodology to the Internet of Things, which is a considerably perspective scope of the research.
References
Chen, F., Deng, P., Wan, J., Zhang, D., Vasilakos, A. V., & Rong, X. (2015). Data mining for the internet of things: Literature review and challenges.International Journal of Distributed Sensor Networks, 11(8), 1-14, Web.
Chye, K. H., Gerry, C. K. L. (2002). Data mining and customer relationship marketing in the banking industry. Singapore Management Review, 24(2), 1-27.
Khodakarami, F., & Chan, Y. E. (2014). Exploring the role of customer relationship management (CRM) systems in customer knowledge creation. Information & Management, 51(1), 27-42.