In today’s business world, information about the customer is a necessity for a businesses trying to maximize its profits. A new, and important, tool in gaining this knowledge is Data Mining. Data Mining is a set of automated procedures used to find previously unknown patterns and relationships in data. These patterns and relationships, once extracted, can be used to make valid predictions about the behavior of the customer.
Data Mining is generally used for four main tasks: (1) to improve the process of making new customers and retaining customers; (2) to reduce fraud; (3) to identify internal wastefulness and deal with that wastefulness in operations, and (4) to chart unexplored areas of the internet (Cavoukian). The fulfillment of these tasks can be enhanced if appropriate data has been collected and if that data is stored in a data warehouse. According to Stanford University, A Data Warehouse is a repository of integrated information, available for queries and analysis. Data and information are extracted from heterogeneous sources as they are generated….This makes it much easier and more efficient to run queries over data that originally came from different sources. When data about an organization’s practices is easier to access, it becomes more economical to mine. “Without the pool of validated and scrubbed data that a data warehouse provides, the data mining process requires considerable additional effort to pre-process the data” (SAS Institute).
There are several different types of models and algorithms used to “mine” the data. These include, but are not limited to, neural networks, decision trees, rule induction, boosting, and genetic algorithms.
Neural networks are physical cellular systems which can acquire, store, and
utilize experiential knowledge (Zurada). Neural networks offer a way to efficiently model large and complex problems. Decision trees are diagrams used for making decisions in business or computer programming. Branches are used to represent choices with associated risks, costs, results, or probabilities. Rule induction is a way of deriving a set of rules to classify cases (Two Crows). These set of rules differ from those in a decision tree in that they are independent from one another. Boosting is a technique in which multiple random samples of data are taken and a classification model for each set of data is made (Two Crows). The genetic algorithm is a model of machine learning, whose behavior is based on the processes of evolution in nature. Populations of data are resented by chromosomes and then go through a process of evolution. The members of one set of data compete to pass on their most favorable characteristics to the next generation of data. This process continues until the best data is found. Many of the models and algorithms used in data mining are simplifications of the linear regression model.
Data Mining is largely, if not entirely used for business purposes. The highest users of data mining include banking, financial, and telecommunications industries (Two Crows).
A survey taken by Two Crows Corporation turned up these applications of data mining:
Ad revenue forecasting
Churn (turnover) management
Credit risk analysis
Food-service menu analysis
Government policy setting
Market basket analysis
New product development
Shelf management/store management
Student recruiting and retention
Data mining will have a different effect on different industries in the business world. In the telecommunications industry, for example, in order to retain or build market share and expand or develop new products and services, service providers will have to make the necessary adaptations and changes that the industry and pace setting technology requires.
“The most successful telecommunications companies will, of course, be the ones who can develop and market products and services that customers will buy,” says Julian Kulkarni, SAS institute Europe’s Product Marketing Coordinator for telecommunications. “But high customer churn rates in telcom markets show that you cannot depend on customer loyalty. To thrive, companies must know their customers, their products, their own operations, and the competition better.”
The key to succeeding in this rapidly changing industry is to understand the customer, or the market that the customer represents. Through data mining, telecommunications companies can know what their customers have done in the past and what they will do in the future. With this information, the companies will be in ideal positions to make business decisions based on the information they have gained from the data mining process.
Other real world examples of data mining include:
Targeting a set of consumers who are most likely to respond to a direct mail campaign
Predicting the probability of default for consumer loan applications
Predicting audience share for television programs
Predicting the probability that a cancer patient will respond to radiation therapy
Predicting the probability that an offshore oil well is actually going to produce oil
There are many computer applications on the market to assist businesses in the data mining process. The applicability of these programs can accommodate the various uses of data mining. Software titles include AC2, ALICE d’Isoft, AutoClass C, C5.0 (See5), Clementine, Data Surveyor, DataDetective, DataEngine, Datasage, DataScope, DataX(tm), DbBridge, dbProbe, dbProphet, Explora, IBM Visualization Data Explorer, INLEN, IRIS, IXL ; IDIS software, LEVEL5 Quest, MineSet (SGI), ModelQuest MarketMiner, Nuggets(TM), Partek, PolyAnalyst, PV-WAVE, SE-Learn, Sipina-W v2.0 ; Sipina-Pro, Snob, SPSS Data Mining Software, The Data Mining Suite, Thinkbase’s Data Mining Product, TiMBL (Tilburg Memory Based Learner), Tooldiag, WINROSA, WinViz, WizWhy, XmdvTool, and XpertRule.
Summary Table (Pryke):
Company Product Major Function URL
Isoft ALICEd’Isoft Alice is a powerful and easy to use Data Mining Tool. Use decision trees to explore & exploit your data. Textual reports, SQL queries generation, What-If Analysis, etc. http://www.isoft.fr/
SPSS Clementine Clementine is the leading data mining toolkit, twice winning the UK Government’s (Department of Trade ; Industry) SMART award for innovation. Clementine applications include customer segmentation/profiling for marketing companies, fraud detection, credit scoring, load forecasting for utility companies, and profit prediction for retailers. http://www.isl.co.uk/clem.html
Data Distilleries Data Surveyor Data Surveyor is a data mining tool for expert users. It consists of a suite of powerful algorithms and provides support for all steps in the knowledge discovery process. Data Surveyor allows the user to interactively discover knowledge, inspect results during discovery and guide the discovery process. Data Surveyor applications include database marketing, credit scoring and risk analysis. http://www.ddi.nl/
MIT DataEngine DataEngine is a software product for data analysis using fuzzy technologies, neural networks, and conventional statistics. It has been successfully applied in the fields of forecasting, data base marketing, quality control, process analysis, and diagnosis.The special features of the new version are on the one hand the high flexibility concerning the integration into existing solutions, which is supported by a flexible ASCII import and the import of MS-Excel files. On the other hand it is possible to include any kind of user defined functions into DataEngine.In addition to this, DataEngine 2.0 becomes the tool for professional data analysis thanks to the 32 bit architecture and the productive graphic component for data visualization. http://www.mitgmbh.de/
DataSage, Inc. Datasage Datasage provides a suite of C++ modules which maintain data inside an existing relational database where it can be managed more effectively, (the company calls this data centricism). Datasage then uses high-speed C++ routines to read and batch process the data. As a result, the product can handle very large databases. Datasage includes a suite of data transforms, modeling and analysis tools, including neural networks and factor analysis. http://www.datasage.com/
Trajecta, Inc. dbProphet Utilizing sophisticated neural network technologies, Trajecta offers a broad range of software and services that provide highly accurate predictions of complex customer behavior and market trends. Trajecta’s non-technical, easy-to-use software can also help optimize business activities, allowing its users to exceed their business goals. http://www.trajecta.com/
Summary Table (Pryke):
Company Product Major Function URL
SGI MineSet (SGI) Combining powerful integrated, interactive tools for data access and transformation, data mining, and visual data mining, MineSet provides you with a revolutionary paradigm for getting maximum value from your vast data resources. MineSet enables you to gain a deeper, intuitive understanding of your data, by helping you to discover hidden patterns, important trends and new knowledge. It is this deep understanding which can be used for developing powerful business strategies leading to greater competitive advantage. http://www.sgi.com/software/mineset/
Data Mining Technologies Inc. Nuggets™ Nuggets uses proprietary search algorithms called SiftAgents(TM) to develop English if – then rules. These algorithms use genetic methods and learning techniques to intelligently search for valid hypotheses that become rules. In the act of searching, the algorithms learn about the training data as they proceed. The result is a very fast and efficient search strategy that does not preclude any potential rule from being found. The new and proprietary aspects include the way in which hypotheses are created and the searching methods. The user sets the criteria for valid rules. Nuggets also provides a suite of tools to use the rules for prediction of new data, under-standing, classifying and segmenting data. The user can also query the rules or the data to perform special studies. http://www.data-mine.com/
Partek Inc. Partek Software for data mining and knowledge discovery based on statistical methods, data visualization, neural networks, fuzzy logic and genetic algorithms. http://www.partek.com/
MIT WINROSA WINROSA is a software tool which generates automatically Fuzzy If-Then Rules from your data. The generated data set can be run by most of the existing fuzzy tools like e.g. DataEngine, fuzzyTECH, and Matlab. http://www.mitgmbh.de/
Attar Software XpertRule Data Mining using high performance parallel SQL technologyA Windows PC client being able to intelligently query the data source on the host server can achieve knowledge Induction. The speed of the process is therefore dependant upon the server – not the speed of the client PC. This allows data mining to exploit the speed offered by MPP servers (Massive Parallel Processors) and database architectures that are optimized for serving queries. http://www.attar.com/
Cavoukian, Ann, Ph.D. “Data Mining: Staking a Claim on Your Privacy.” Jan. 1998
Pryke, Andy. “The Data Mine.” 23 Sep. 1998
SAS Institute Inc. “Data Mining.” 12 Jan. 2000
Two Crows Co. “Introduction to Data Mining and Knowledge Discovery.” 1999
Zurada, J.M. (1992), Introduction To Artificial Neural Systems,
Boston: PWS Publishing Company, p. xv: