A Review of Data Mining Tools In Customer
Relationship Management
Jayanthi Ranjan, Institute of
Management Technology, Ghaziabad , Vishal Bhatnagar, Indraprastha University,
Delhi
ABSTRACT:
Data mining uses a combination of an explicit knowledge base, sophisticated analytical skills, and domain knowledge to uncover hidden trends and patterns. These trends and patterns form the basis of predictive models that enable analysts to produce new observations from existing data. The paper presents the review of various Data Mining (DM) tools in Customer Relationship Management (CRM). There are number of data mining tools available in the market spaces that can provide the cutting edge for the firms to achieve profitable CRM. The paper explores features available in various tools that can help the firms to decide the best tools according to their needs and requirements. The paper compares various data mining tools that help the enterprises in decision making.
Keywords: Data mining, Customer Relationship Management (CRM), Customer retention, DM tools
1. Introduction
Data mining is the search for relationships and global patterns that exist in large databases, but are “hidden” among the vast amount of data (Saraee et al, 1998). These relationships represent valuable knowledge about the database and objects in it. The process of Data Mining helps firms to analyze the customer data and extract the useful information, to gain competitive advantage over others. (Hui and Jha, 2001) described the database of customer service as a repository of invaluable information and knowledge that can be utilized to improve customer service. Chen and Liu (2005) studied applications of data mining in bioinformatics, information retrieval, adaptive hypermedia and electronic commerce, which require interaction with the customer. (Chang et al, 2002) discussed the importance of customer relationship management in enchasing the ability of a firm to compete and retain key customers. CRM as described by (Kwok et al, 2007) is Strategic Customer Relationship Management System (SCRMS) which collects, integrates and diagnoses various customer-related data from different operation systems in departments within an enterprise. (Panagiotis et al, 2007) defines CRM as optimizes values as profitability, revenue and customer satisfaction (what and why) by organizing around customer segments, fostering customer-satisfying behaviors and implementing customer-centric business models (how).
Data mining tools helps CRM by providing the complete framework, which covers:
Ø To analyze the business problem.
Ø To prepare the data requirements.
Ø To build the suitable model with respect to business problem.
Ø To validate and evaluate the designed model.
The analytical engine of the data mining tool helps to discover the hidden patterns that help the firms in decision making. Earlier data mining tools used to focus on analytical problems that are on discovering the hidden patterns. Slowly the focus turned to other concern of the Data mining like the data preparations, model building and evaluation of models. The data preparation is vital for the success of CRM as the data for the tools comes from various sources. So the missing data, outlier and other necessity work is carried in data preparation phase. To standardize the process of data mining the CRISP-DM model is proposed which ensure that the standard required for the data mining is maintained. The model of CRISP-DM has phases which ensure a standard required for the Data mining process.
Model building is the next phase of the Data mining tool, which builds the various models according to the data given in the data preparation phase. The last phase is the evaluation of the model, so that the proper results in the form of useful patterns can be drawn from the models built by the tools.
The tools of data mining for CRM should be able to detect the necessary information from the available data .To achieve this, Data mining tools should have some characteristic like:
Ø User friendly environment
Ø Efficiency of the tool
Ø Basic task should be accomplished
Ø Low cost of implementation
Competitive firms with a future vision uses data mining to reduce fraud anticipate resource demand and curb customer attrition, CRM Today (2003). As pointed by (Spangler et al, 1999) Availability of detailed customer data and advances in technology for warehousing and mining enable firms to better understand and serve their customers. This raises the concern over the issue of privacy of customer data, but the early adaptation of information technology in their business has gained them competitive advantage over others.
The objective of the paper is to describe the power of the Data Mining tools in bringing the useful information in the form of patterns, which are helpful for the companies to maintain a good customer base by using CRM. We believe that the correct usage of the tools of the Data Mining can lead to a substantial rise in the profit of the firms.
The paper is organized as follows: Section II presents the related research. Section III discusses customer relationship management. Section IV explores Data mining. Section V addresses about Data mining tool applications in CRM. Section VI shows data mining tool and its selection for CRM. Section VII presents comparison of various Data mining in CRM. Section VIII addresses the Limitations of applying Data mining in CRM and Section IX concludes by urging the firms to applying the Data mining tools in successful CRM.
2. Motivation
And Related Work
There are many data mining tools suggested by different vendors for different sectors of businesses. The application of which tool is suitable for a particular CRM application depends upon the matching characteristics of the tools to that of the requirement. This requires that the features of the tools should be available to the users in brief to take quick decision. The suitable application of data mining tool in CRM is much widely explored.
The work by Nisbet (2004) discusses about suitable Data Mining tools for CRM. Saarenvirta (1998) explores customer data mining. (Wong et al, 2004) examines intelligent Data Mining for CRM. Berson, Smith and Thearling (1999) explain about building Data Mining application for CRM, Siragusa (2001) argues about implementing Data Mining for better CRM. Mukhopadhyay and Nath (2001) emphasized on importance of measuring the efficiency of CRM systems and proposed an efficiency model for the same.
Berson et al (1999) recommended a simple method to evaluate the benefits of a data mining model for the CRM applications. Vince Kellen (2002) is of the view that how a company measures its CRM activities depends upon who is doing the measuring and what activities are being measured. Rigby and Ledingham (2004) suggested a model to calculate the cost of CRM. (King et al, 1998) evaluated the fourteen desktop data mining tools. (Collier et al, 1999) describe a methodology for evaluating and selecting data mining software. Runsala (2003) describes a tool called Lou that is considered to overcome the limitations of the various data mining tools like the cost and user friendly aspect of the tools.
3. Customer
Relationship Management
Customer Relationship Management (CRM) is about managing business interactions with the customer. (Jutla et al, 2001) describe CRM as acquiring, analyzing and sharing knowledge about and with customers. CRM help firms to stream customer services and centralize the customer data for analysis purposes. (Bueren et al, 2004) is of opinion that CRM aims at leveraging investments in customer relation to strengthen the competitive position and maximize the returns.
Customer relationship management (CRM) is a process that manages the interactions between a company and its customers. Customer relationship management (CRM) is a process that manages the interactions between a company and its customers. CRM is a strategy that integrates sales, marketing and service which unites operating procedure and technologies to better understand customer from different perspectives. CRM encompasses all measures for understanding the customers and for exploiting this knowledge to design and implement marketing activities, align production and coordinate the supply-chain (Srivastava, 2004). As pointed by Robert Kapanen (2004) Customer relationship management is a framework for developing both the business processes and the supporting infrastructure to improve service delivery.
CRM solutions focus on automating and improving business processes in
front-office areas such as marketing, sales, customer service and support. CRM
provides an integrated view of customer interactions starting with software
applications that captures these interactions. Customer Relationship Management
(CRM) helps a firm to streamline customer services and to centralize its
customer’s data for analysis purposes. As pointed by Alt and Puschmann
(2004) CRM is understood as a
customer-oriented management approach where information systems provide
information to support operational, analytical and collaborative CRM processes
and thus contribute to customer profitability and retention. CRM as described
by
4. Data
Mining
Data mining is the detection of relevant patterns in large pool of data. Thearling (1998) opinions that Data mining uses well-established statistical and machine learning techniques to build models that predict customer behavior. Today, technology automates the mining process, integrates it with commercial data warehouses, and presents it in a relevant way for business users. Data mining integrates various technologies like databases management, machine learning, statistics, parallel processing and visualization. Data mining applies techniques like neural networks, rule deduction and generation, regression analysis, genetic algorithms etc to analysis data and finds the hidden patterns from the databases. Data mining reveals information’s which are helpful for the companies to take crucial decisions for the growth of the companies. Data mining uses the extracted information from large databases to make critical business decisions (Cabena et al, 1998).
Data mining tools are most effectively used with data stored in data warehouse or data marts (Kleisnner, 1998). Data mining is a process which requires the continuous cycle means that once the data mining evaluates and finds some patterns then that patterns will be used for further evaluation work. Data mining empowers the knowledge workers to more deeply and better understand the business and their customer, which helps in the profits for the firms. Data mining as pointed out by Han and Kamber (2006) is extracting or mining knowledge from large amount of data. Data mining as described by Holshemier and Siebes (1994) is the search for relationship and global pattern that exists in large databases but is hidden among the vast amount of data.
The techniques of data mining like Classification, Prediction, clustering, association, genetic algorithms and neural network help achieve the goal of the data mining to extract the hidden, unknown patterns from the database. The classification is used in Data Mining to classify the data or element into one of the group based on the data available. Prediction is used to predict the future trends in the business based on the data available. The classification as described by Han and Kamber (2006) is a two step process: in the first step, a classifier is built describing a predetermined set of data classes called as learning step. In the next step the classification is actually performed. Ahmed (2004) points Classification as the way to discover the characteristics of customers who are likely to leave and provides a model that can be used to predict who they are. Hand et al (2001) mention that patterns occur frequently during Data Mining process. A frequent occurring subsequence such as customer buying bread with butter is very easily found. A cluster as described by Han and Kamber (2006) is a collection of data objects that are similar to one another within the same cluster and are dissimilar to the objects in other clusters. The cluster detection algorithm searches for groups or cluster of data elements that are similar to one another. K-means is one of the major methods of clustering. It aims at partitioning the data that have similarity and distinguishing it with other different one. Ahmed (2004) discusses about using clustering which helps the data-mining tool discovers different groupings with the data. This can be applied to problems as diverse as detecting defects in manufacturing or finding affinity groups for bankcards. Association discovery algorithms find combinations where the presence of one item suggests the presence of other .The association algorithms derive the association rules systematically and efficiently.
5. Data
Mining Tools Applications In CRM
Virtually any
process from pharmacology to customer service can be studied, understood, and
improved using data mining. The top three end uses of data mining are, not
surprisingly, in the marketing area.
Figure 1: Data Mining Applications
Useful For Companies
(Adopted
from http://www.informationweek.com/673/73iudat.htm)
Figure 1 shows that the Customer demographics are one of the most important applications for the companies. The application of Data Mining tools are in:
Ø Customer Profiling: In customer profiling, characteristics of good customers are identified with the goals of predicting; who will become one and helping marketers target new prospects. Data mining can find patterns in a customer database that can be applied to a prospective database so that customer acquisition can be appropriately targeted. For example, by identifying good candidates for mail offers or catalogs direct-mail marketers can reduce expenses and increase their sales. Ansari et al (2001) proposed high-level system architecture for applying the data mining process for managing customer interaction. Ahmed (2004) points that data mining technologies can identify and classify the prospective clients using the user given data. Wang and Wang (2007) points data mining techniques for the online customer segmentations.
Ø Targeted Marketing: Targeting specific promotions to existing and potential customers offer similar benefits. Chiranjeev Bordoloi (2000) discussed a framework for the CRM success and had given necessary steps for the implementation. Ahmed (2004) discussed about the Data mining software tools that uses the business data as raw material using a predefined algorithm to search through the vast quantities of raw data, and group the data according to the desired criteria that can be useful for the future target marketing.
Ø Market-basket analysis: Market-basket analysis helps retailers understand which products are purchased together or by an individual over time. With data mining, retailers can determine which products to stock in which stores, and even how to place them within a store. Data mining can also help assess the effectiveness of promotions and coupons. Michael Meltzer (2000) exhibits model which combines technology, data mining and the business problems together in a single view.
Ø Manage customer relationship: Another common use of data mining in many organizations is to help manage customer relationships. By determining characteristics of customers who are likely to leave for a competitor, a company can take action to retain that customer because doing so is usually far less expensive than acquiring a new customer. Edelstein (2001) discovered building profitable customer relationship with data mining.
Ø Fraud detection: Fraud detection is of great interest to telecommunications firms, credit-card companies, insurance companies, stock exchanges, and government agencies. (Chen et al, 2005) discuss about the data mining application in CRM of credit card business. The aggregate total for fraud losses is enormous. But with data mining, these companies can identify potentially fraudulent transactions and contain the damage. Ahmed (2004) discussed the most important application of data mining are reduce the fraud, to improve customer acquisition and retention. Seifert (2004) pointed that data mining should be used as a means to identify terrorist activities, such as money transfers and communications, and to identify and track individual terrorists themselves, such as through travel and immigration records.
Ø Anticipate and prevent customer attrition: The data mining tool can help to find the customers which are not satisfied by the firm’s services. This helps the firms to give promotional services to group of customers who are likely to attrite. Lejeune (2001) discussed the impact of applying the data mining technique on churn management.
Ø
Mine unstructured data, such as text: The text data is always
unstructured. So data mining tools can help to mine the unstructured data to
help the various organizations to get good out of the data. Carbone (2000)
showed the application of the data mining in the field which has the data from
multiple sources.
6. Data
Mining Tools And Their Selection For CRM
There are many data mining tools available in the vendor space. Nisbet (2004) pointed out that there are no best tools overall as each tool suite has its strengths and weaknesses; each tool suite may be the best for particular needs in particular companies. Each tool have got there own Followers according to the need of the firms. But the most frequent data mining tools in use for the CRM purpose are SAS, SPSS, ORACLE and Insightful miner (2007). They provide the features to its user that helps the firms to achieve profit. They are:
Ø
Seek and retain most profitable customers: By using demographic and
customer data, firms can develop lifelong relationships with most profitable
customers, anticipating and fulfilling their needs.
Ø
Segment markets for a targeted approach: With targeted marketing
campaigns firms can dramatically increase response rates, analyze clickstream
data and sharpen sales strategies.
Ø Predict the future and identify factors to secure desired effects: By applying data mining techniques, organizations can anticipate problems before they occur, forecast resource demands, and fully exploit data about buying patterns to gain a greater understanding of consumer motivations.
Ø Improve customer acquisition and retention: The Data mining tools help in customer acquisition and retention for the firms which are very important for them in the growing competitive atmosphere.
Ø Increase customer lifetime value: These tools help in increasing the life time value of the customer.
Ø
Detect and minimize risk and fraud: These tools help the banking
and financial sectors to detect the fraud and minimize the risk of lose.
Ø
Reduce cycle time while maintaining quality in product development: These
tools also help in reducing the cycle time of the product life cycle.
Ø
Support scientific research: These tools help the scientist in the
research and development by providing the necessary forecasting the finding the
hidden patterns.
Ø
Identify potential respondents: These tools help the firms to find the
right group of customers for their product.
Ø
Discover which customer groups buy specific products: They also
help in finding the customer group which has to be targeted for the specific
product.
Ø
Identify which customers will most likely defect: These tools also
help in identifying the customer likely to churn.
Ø Predict which customers are likely to repay their loan on time: They also help the firms identify there loyal customers.
So the various tools in the market are meeting the demands of the firms for the profitable CRM. The only thing which should be taken care before applying the tools is the analysis of the specific requirement of the firms which help to decide the proper tool according to the requirement. Metagroup (2004) gives the evaluation of graphical representation of the data mining tools in Figure 2.
Figure 2: The Response Of Various
Tools In Graphical Form In The Market
(Adapted from www.oracle.com/technology/products/bi/odm/pdf/odm_metaspectrum_1004.pdf)
The numbers of tools available in the market for effective CRM are many in number. So the difficulty lies with the way how to choose the best tool according to our need. The selection of the tools also depends on the critical success factor of the firms. At any point of the time while implementing the CRM using the Data mining tools the basic objectives of the concern to a firm has to be remembered. Some time the implementation of the CRM using Data mining tools leads to the downside as the basic objectives of the firms are over-shadowed by this concern. So the tools which are selected by the firms should be able to provide the whole framework which is of importance to the firms which include profitable CRM as one objective. There are some basic questions which firms should answer before taking any decision on selection of a tool like is the tool being used in other firms with the same needs as we have or what is the accuracy of the tool for the application we planned or is the tool user-friendly in nature? The other parameter, which needs to be checked, is that the tool should support data preparation phase of CRISP-DM model and does the tool support the data format we have in our firm. CRM Today (2004) describes the guide to evaluate CRM software.
Selecting a proper tool of Data mining for CRM purpose is a challenging task. Some parameter taken under considerations are like the tool should be able to work with the existing applications, it should be cost effective, it should build the model in quick time, the nature of the algorithms supported by the tools and also the time required for the implementation.
These questions can vary from firms to firms, but this question can definitely help the firms to take some tools out of the enormous tools available. Then the firms can go for the in depth study to analyze the features of the left out tools for the one with the best suitability. (Hui and Jha 2001) described the application of data mining techniques to extract knowledge from a customer service database for improving customer service support The firms need to understand this that effective implementation of the CRM using Data mining tool is a Long process which require a continuous effort from the all the departments which are involved in this development. Then only the profitable CRM is achievable through the application of Data mining tool.
7. Comparison Of Various Tools Of Data
Mining For Effective CRM.
In the growing competitive business
world, the competition among the tools of Data mining for CRM available in the
market has also increased. This has created confusion for the firms to choose
the best tools which will cater there needs. We tried to give brief features of
some of the Data mining tools for effective CRM. Table 1.0 refers to the
comparison of features of the various data mining tools for effective CRM