Visualization method for customer targeting using customer map
Introduction
The unified goal of all business strategies is profit directly or indirectly. Over the next decade, thousands of business came to realize that their most important assets are their human assets—their customers. Also, businesses realized that to build winning strategies, they have to find ways to attract and develop the right human assets and keep them. Researches say that companies will be more successful if they concentrate on obtaining and maintaining a share of each customer (Bloch and Pigneur, 1999, Haley, 1968, Tasi and Chiu, 2004, Weinstein, 1994). Furthermore, it has been proven that business strategies which concentrate on finding and keeping good customers continue to generate superior values (Weinstein, 1994). From these researches, it can be said that the core of value creation through customers is finding and keeping right customers who are profitable or have potential profitability. These ideas are encapsulated in customer targeting, which we will propose in this paper.
Target market identification, evaluation, and selection are considered to be necessarily undertaken prior to determining specific strategies in the customer-centric environment. After finding right customers, the company should resolve their needs, and satisfy them. These efforts are linked directly to keeping and acquiring profitable customers and gaining profit from them (Jonker, Piersma & Poel, 2004). To find target customers, customers have been examined and segmented in terms of their information. Many segmentation techniques have been invented and examined as one of the targeting methodologies. They have been invented according to data sources, and they have been approved their virtues.
In the literature, segmentation methods for customer targeting have been developed from demographics, psychographics, usage, behavioral, value, and needs based segmentation successively (Weinstein, 1994). Most of segmentation models have a shortcoming that they use customer data individually. They neglect the opportunity of maximizing the efficiency they can get when they integrate them. Without the integration, decision-makers cannot target a homogeneous segment, but gets several different targets according to data sources and targeting objectives. They have difficulties in deriving efficient strategies from target customers who are dissimilar with their information. For example, a VIP segment which is derived in terms of customer value can be totally different with their characteristics or needs. In that case, they do not get knowledge of how they select the target because the customers are different in their characteristics and what they do for the customers because the customers are heterogeneous in their needs. If the target segment is homogeneous with all the aspects; characteristics, value, and needs, it is easy to select the target, satisfy them and finally create value from them.
In addition, existing targeting models and mining techniques for targeting are lack of ability of knowledge presentation to visualize and present the mined knowledge to the decision-maker. Especially for senior managers, visualization tools are very useful because of their quick and easy knowledge discovery without preconception (Greenberg and McDonald, 1989, Hwang et al., 2004, Kim and Street, 2004, Mitchell, 1994, Peltier and Schribrowsky, 1997, Teal, 1991, Westphal and Blaxton, 1998).
In this paper, we will unify the scattered concepts of customer segmentation and the basic analytical structures of customer-centered marketing based on their pivotal goal, customer targeting. This unified model will be incarnated in the customer map. The customer map is a novel technique to find right target customers who are homogeneous with characteristics, value and needs. The model integrates numerous customer data from various data sources. Then, it will derive key information to build the axes of the customer map using data mining techniques and visualize the information using the customer map. The customer map derives target segments with their values, and guides marketers to building strategies for keeping and acquiring right customers from their characteristics and needs. It also affords to monitor and perceive real-time state and the change of the customer value distribution based on their information without preconception.
We will apply the customer map in a Korean credit card company, and suggest how to derive strategies from the customer maps obtained from its data. Finally, the customer map will be developed into a web-based system. Using the customer map and its implemented system, the company will increase the efficiency of customer targeting and achieve value creation through the customer more easily.
Section snippets
Literature review
Customer targeting is finding and keeping right customers, who are profitable and loyal. Customer segmentation is the prerequisite for customer targeting. It involves the subdivision of entire customers into smaller customer groups of segments, consisting of customers who are relatively similar within each specific segment (Weinstein, 1994). The assumption underlying segmentation is that customers vary widely with respect to their needs, preferences, behaviors and any kinds of information. To
Customer targeting process
Customer targeting is a process of building strategy towards specific customers. It is aimed to find customers who conform to decision-makers' interests, and to establish marketing plans for them. For successful customer targeting, we should decide dimensions of customer targeting which reflect the kernels of customer targeting. The first dimension is a goal of customer targeting. The goal can be to increase customers' current value, to increase their potential value, to decrease their costs,
Applying the visualization targeting model to a credit card company
In this paper, our proposed model applied its framework to a service industry especially to a credit card company. The company handles tremendous VOC from call centers and performs the CSI survey twice in a year. Also, it maintains various kinds of customer information in the data warehouse. With VOC and CSI data, we could derive key customer needs to build the customer map. The company has collected almost 240,000 samples of VOC data which are mainly classified into complaint, and used 3200
Conclusion and further research
We suggested the customer map, the visualization method for customer targeting. The customer map is a visualization tool that identifies the homogeneous target group in terms of customer needs, customer characteristics, and customer value. Moreover, the customer map enables decision-makers to derive business strategies for customer targeting. The customer map has a meaning that it is a systematic tool to build the customer-centered strategy, CMRA strategy which is a core enabler of value
References (17)
- et al.
Joint optimization of customer segmentation and marketing policy to maximize long term profitability
Expert Systems with Applications
(2004) - et al.
An intelligent system for customer targeting: A data mining approach
Decision Support Systems
(2004) - et al.
The use of need-based segmentation for developing segment-specific direct marketing strategies
Journal of Direct Marketing
(1997) - et al.
The extended enterprise: A descriptive framework: Some enabling technologies and case studies in the Lotus Notes Environment
Strategic Information Systems
(1999) - et al.
Optimal database marketing: Strategy, development, and data mining
(2002) - et al.
Successful needs/benefit segmentation: A user guide
Journal of Consumer Marketing
(1989) Benefit segmentation: A decision-oriented research tool
Journal of Marketing
(1968)- et al.
An LTV model and customer segmentation based on customer value: A case study on the wireless telecommunication industry
Expert Systems with Application
(2004)
Cited by (51)
Predicting millionaires from Ethereum transaction histories using node embeddings and artificial neural nets
2023, Expert Systems with ApplicationsMultidisciplinary Pattern Recognition applications: A review
2020, Computer Science ReviewAnalysis for customer lifetime value categorization with RFM model
2019, Procedia Computer ScienceCustomer Selection Utilizing Big Data Analytics
2015, Handbook of StatisticsCitation Excerpt :In 2000s, much more resources became available (e.g., various data sources, large databases, improved computing power), and new approaches based on data mining techniques have been tried. For example, Chou et al. (2000) describe data mining techniques designed to address the problem of selecting prospective customers from a large pool of candidates, Shaw et al. (2001) have a good review of how data mining can be integrated into a knowledge-based marketing, Kim and Street (2004) propose a data mining approach to select an optimal target point where expected profit from direct mailing is maximized, Woo et al. (2005) suggest a “customer map,” which is the visualization method for customer targeting based on data mining techniques, and Lawrence et al. (2007) describe the analytics-based solutions to identify new sales opportunities and to estimate future revenue opportunities. In this chapter, we try to expand the customer selection problem to a specific domain of demand response (DR) program targeting based on big data analytics using proper data mining techniques.
Determining a Revenue Generating Model that Creates Customer Value by Using a Skip-the-line Application in Romania
2023, European Journal of Interdisciplinary Studies