Applications of Data Mining
The purpose of the present document is to discuss various applications of data mining. This essay begins the topic of applications of data mining with the retail and customer service domain. The focus of this part of the discussion examines customer relationship management and employee relationship management. Applications of data mining within the field of education follows business applications. The third major section discussed is biology. The fourth major section discussed is tourism. Data mining applied to social media is the last major section. Finally, a discussion on information security, arguably the most important of these subsections, is explored. The essay closes with a summary section of key points discussed.
Customer Relationship Management
Customer relationship management (CRM) refers to specific tools and processes that are marketed to large organizations as a way to drive their customer interface while integrating and aligning core information systems and business processes. Retaining customers is the core of CRM concepts, for example, customer equity.  For customers must be understood on a per-customer basis to identify their needs, preferences, and potential.  Data mining plays an important role in CRM by providing insight into raw customer data.  Muley attribute data mining success as a result of increased storage capacity.  When effectively integrated into the organization, there is internal leadership, culture, business processes, organizational structure, and information systems comprising “external customer touch points”. 
CRM is most effectively applied to service and retail organizations. It has been applied to manufacturing agencies; however, B2B communication systems established themselves as the service economy.  The internally focused employee-organization relationship (ERM) is a companion to CRM that facilitates effective employee management. Retail and service companies innately have unique behaviors, infrastructure concerns, operational dimensions, and challenges that influence how service personnel and representatives interact with customers either nurturing or damaging the customer’s perceptions and attitudes toward the brand. 
In 2002, Meredith argued that CRM was not a breakthrough, leading edge, or new—simply, the basis of a market economy.  Though as a new information technology (IT), CRM offers attractive advantages gained in customer servicing by applying technologies similar to those that manage communication and information to collect and organization information about each customer that is presented to their frontline employees.  The Siebel Systems is a leader in the market. Its CRM architecture reveals the system’s limitations (See Figure 1). A key limitation is the absence of cross-functional links between the business and the internal department units.  Additionally, it assumes that all customer information will be received by a single central database that is accessible by all employees that will need it, not limited to the external customer service workforce. 
Figure 1. Siebel Systems CRM Architecture
Typically, there will be multiple databases containing valuable customer information. Additionally, there might be important customer information recorded in a paper-based filing system. the Siebel System focuses exclusively on the IT domain. Doing so, it fails to support the needs of the infrastructure. Kline explains that developing a customer-centric infrastructure requires between 60 and 70 percent of the work to happen below the surface.  Recognizing that team leaders continue to struggle with effectively managing of customer retention, motivated Ascarza et al., to create a framework that utilizes a holistic approach to customer retention.  The framework begins with foundational data and methods, a single campaign design and tailored management approach, coordination across several campaigns, and the integration with the firm’s marketing strategy. 
Customer retention as defined by Ascarza et al., “is the customer continuing to transact with the firm” (p. 5).  That definition emphasizes retention as something the customer does that might affect the business. The distinguishing agent in their framework is the cultivation of individual retention campaigns. Their framework expands on current practice by recognizing the customers at highest risk of not being retained might not overlap 100% with customers that should be targeted.  The opposite of customer retention is known as “churn” (p. 6) . In 2011, Sharma and Panigrahi defined churn as a customer leaving one company to go to another company.  Ascarza’s team recommends that predicting churn is one of various inter-related elements influencing customer retention management.
Educational Data Mining
The second application of data mining, education, is a fertile field of interdisciplinary research. Educational data mining EDM focuses on data that originates in an academic context. EDM applies computational approaches to answer questions and find solutions important to the field of education.  EDM utilizes algorithms over various kinds of educational data to support machine-learning, statistics analysis, and data-mining.  The main goal of EDM is to analyze all kinds of educational data to find solutions to issues raised by educational researchers by developing methods to understand the unique data types comprising educational settings and ways in which students learn.
EDM has generated instrumental educational software and huge repositories of information on students maintained at the state level. Utilizing the Internet for teaching and learning has generated a new context named e-Learning or web-based education. There is a huge amount of information about the teaching-learning interaction. This body of information can provide a gold mine of educational data.  A central application for e-Learning and learning management systems (LMS) is providing online instruction. Additionally, provide collaboration, communication, administration and reporting tools. Statistical and psychometric culled from web mining (WM) has been applied to student performance, student behavior, and curriculum development from data entirely gathered in classroom environments.  The Adaptive Educational Hypermedia System (AEHS) and Intelligent Tutoring System (ITS) are alternatives to the “just-put-it-on-the-web” approach tailored to the needs of a particular student. EDM has been utilized by data picked up by log files and user models. 
The recent strategies used to process information contained in scientific documents using online tools as ignited a revolution in the third application of data mining targets the field of biology. The field of biology in terms of the volume of data and the access to knowledge hidden in text is a wealth of information.  In 2015, Krallinger used biological text mining and information extraction systems to exploit word regularities and recurrent natural language expressions used when describing biologically relevant data in journal articles. Krallinger asserts that there is a “considerable amount of biological information” (p. 6).  Text-mining allows for the extraction of information from semi-structured database records.  That approach supported the classification, analysis, and the extraction and evaluation of text mining applications.  The author developed validation sets for text mining in hepatotoxic compounds and the interaction and localization of the Arabidopsis thaliana protein interaction. Krallinger’s efforts demonstrate the feasibility to integrate text mining systems that are based on supervised machine learning approaches to the entire body of literature allowing for the text classification scores that enable heterogeneous types of bio-entities to be prioritized. 
Applying hybrid text-mining techniques to smart destination management allows researchers to analyze travelers’ online reviews of specific cities collected from www.virtualtourist.com. The reviews fell into fifteen categories: sightseeing, restaurants, nightlife, hotels, things to do, shopping, outdoors, favorites, off the beaten path, overview, transportation, what to pack, tourist traps, warnings, and low level of service quality.  The information is collected from personal blogs and online review sites. This source of information provides insights to tourism destinations on important service areas to improve. When traveling abroad, language discrepancies often emerge for travelers and the online travel recommendation systems.  The Jaccard Distance Score estimates the language discrepancies between destination marketers and travelers in their descriptions of the travel experience across eleven tourism destinations in the United States. Text mining made it possible to identify the difference in the language used by travelers compared to that used by Visitors’ Centers and Convention websites on various themes. By identifying discrepancies, marketers can improve communication with travelers more effectively online.  In a recent study, the investigator asked if text mining could effectively analyze consumer generated online content gathered from hotel reviews. Specifically, the examiner attempted to demonstrate how helpful text mining is for service oriented firms. By analyzing sentiments, data, topic classification provided by hotel guests business leaders will gain valuable insights that can provide an edge over competitors. 
The growing reliance on social media networks encourages data mining techniques that can enable reforming the unorganized data and placing that information in a systematic pattern. The significance of social media research largely follows either social media’s intersection with academia or the industry.  Social media data is largely unorganized and present in the form of images, videos, texts, and voice . This exponentially growing leviathan of information must be placed or clustered into systematic patterns.  Presently, 19 social media data mining techniques have been recorded in the literature. Those techniques attempt to address nine discrete research goals across six unique services and industrial domains. Still data mining of social media remains raw and is fertile group for more effort by academia and industry to perform that job adequately. 
Largely in part to the recent Facebook scandal, data mining and information security have been linked in the social discussion surrounding these topics. How does information security contradict data mining? Data mining is important in information security, as it can keep the individual’s personal data safe or unleash it to the world. This field is newly being explored and is one of the most up and coming topics to be studied in the future of data mining, as it combines the previously discussed sections and adds a personal layer to them. How data mining and information security can develop together will be at the forefront of discussions for years to come.
The purpose of the present document was to review diverse data mining techniques applied across five domains. Within the business sector, data mining techniques applied to customer retention, predicting churn, and employee relationship management served as launchpad for the present discussion. The study conducted by Keramati, Ghaneei, and Mirmohammadi created a model that would predict customer churn from electronic banking. 
In the field of education, adaptive educational hypermedia systems were presented as an alternative to the trend of simply uploading education related content to the web. In the biology section, the feasibility and significance of Krallinger’s text-mining research was described. The most salient point that emerged from the discussion on tourism was the issue of conflicting ways that tourists described regional processes, sites, and activities revealed important insights from effectively mining data gathered from travel blogs and personal reviews. Social media remains a rapidly growing body of unorganized data that requires effective mining techniques.
 F. L. Eichorn. 2004. “Internal Customer Relationship Management (IntCRM): A Framework for Achieving Customer Relationship Management from the Inside Out. Problems and Perspectives in Management,” 2(1), 154-177.
 B. H. Meredith. 2002. “Making CRM work.” NZBusiness Nov.
 H. Kline. 2001. “CRM: Overcoming the Infrastructure Hurdle.” Business Communications Review, July.
 E. Ascarza; S. A. Neslin; O. Netzer; Z. Anderson; P. S. Fader; S. Gupta; B. G. S. Hardie; A. Lemmens; B. Libai; D. Neal; F. Provost; and R. Schrift. 2017. “In Pursuit of Enhanced Customer Retention Management: Review, Key Issues, and Future Directions. Paper presented at the 10th Triennial Invitational Choice Symposium, University of Alberta, 2016.
 R. T. Rust; J. Kim; Y. Dong; T. J. Kim; and S. Lee. 2015. “Drivers of Customer Equity,” Handbook of Research on Customer Equity in Marketing. E. Elgar, 17-43.
 S. De Cnudde; and D. Martens. 2015. “Loyal to Your City? A Data Mining Analysis of a Public Service Loyalty Program.” Decision Support Systems (pp. 74-84). Antwerp, Belgium. DOI: http://dx.doi.org/doi: 10.1016/j.dss.2015.03.004
 S.-L. Pan; C.-W. Tan; and E. T. Lim. 2006. Customer Relationship Management (CRM) in e-government: A Relational Perspective. Decision Support Systems 42(1), 237-250.
 S. Lessmann; and S. Voß. 2009. “A Reference Model for Customer-Centric Data Mining with Support Vector Machines.” European Journal of Operational Research, 199(2), 520-530.  C. Romero; and S. Ventura. 2010. “Educational Data Mining: A Review of the State of the Art.” IEEE Transactions on Systems, Man, and Cybernetics—Part C. Applications and Reviews, Vol. 40(6), 601-618.
 T. Barnes; M. Desmarais; C. Romero, and S. Ventura. 2009. Paper presented at the 2nd International Conference on Educational Data Mining. Cordoba, Spain.
 J. Mostow; and J. Beck. 2006. “Some Useful Tactics to Modify, Map, and Mine Data from Intelligent Tutors.” Journal of Nat. Lang. Eng., Vol. 12, no. 2, (pp. 195-208).
 M. Krallinger. 2015. “Development, Application and Evaluation of Text-Mining methods for Biomedical Literature Processing: From Document Categorization to Gene Ranking.
 V. B. Bajic; M. Veronika; P. S. Velandandi; A. Meka; M. W. Heng; K. Rajaraman; H. Pan; and S. Swarup. 2005. “Dragon Plant Biology Explorer. A Tex-Mining Tool for Integrating Associations Between Genetic and Bio-chemical Entities with Genome Annotation and Biochemical Terms Lists.” Plant Physiol., 138, 1914-1925.
 Special Issue on “How Technology-Enhanced Tourism is Transforming Societies, cultures, and Economies.” 2017. Technological Forecasting & Social Change, http://dx/dpo/prg/10.1016/j.techfore.2017.06.019.
 M. A. M. Injadat; and A. B. Nassif. 2016. “Data Mining Techniques in Social Media: A Survey.” Neurocomputing. Http://dx.doi.org/10.1016/j.neucom.2016.06.045.
 A. L. Kavanaugh , E. A. Fox, S. D. Sheetz; S. Yang; L.T. Li; D. J. Shoemaker, et al., “Social media use by government: From the routine to the critical.” Gov. Inf. Q. 29 (2012), 480-491. DOI: 10.1016/j.giq.2012.06.002.
 A. Garant. 2017. “Social Media Competitive Analysis and Text Mining. A Case Study in Digital Marketing in the Hospitality Industry.” Bachelor’s Thesis. Aalto University.
. A. Keramati; H. Ghaneei; and S. M. Mirmohammadi. 2016. “Developing a Prediction Model for Customer Churn from Electronic Banking Services Using Data Mining.” Financial Innovation, 2(10). DOI: 10.1186/s40854-016-0029-6.
. A. Sharma; and P. K. Panigrahi. 2011. A Neural Network Based Approach for Predicting Customer Churn in Cellular Network Service. International Journal of Computer Applications, 27(11), 26-31.
. F. Conen. 2011. “Data Mining: Past, Present, and Future.” The Knowledge Engineering Review, 26(01), pp. 25-29.