Data mining is part of a group of concepts or techniques related to business intelligence, or e-business intelligence. Data mining involves obtaining information from a variety of sources that is stored in a data warehouse. This information becomes the input for various applications that uncover relationships and trends related to customers and processes. Online analytical processing (OLAP) allows a user to view data from many different angles to uncover correlations and relationships, somewhat like a Rubik's cube (Roberts-Witt, 2001). These results are then used by managers and others to make better decisions. The emphasis is on data sharing where the web allows various types of information to be accessible to the masses. Managers, customers, suppliers and partners can ask the data warehouse questions about various aspects of the business through query and reporting applications. The illustration below provides a graphic view of the data mining concept.

Three important considerations include: clean data, security and scalability (Roberts-Witt, 2001). Where thousands of people are accessing a system, the data must be accurate and free of errors and inconsistencies. Special attention must be given to establishing who has access rights to the data and to enforcing those rights. The infrastructure must be in place including web servers, report servers, databases and networks to support scalability. 

Examples

Starbucks uses data mining to reduce insurance claims. The data is analyzed to uncover locations, floor designs and time patterns where customers slip and fall more frequently from coffee spills (Roberts-Witt, 2001). 

Dow Jones Interactive Wall Street Journal uses data mining to better understand how the site is performing by correlating the log and click-stream information generated with the customer files (Roberts-Witt, 2002). 

The Royal Dutch/Shell Group operates in 135 countries with 90,000 employees and 1,700 separate operating companies. Shell's data mining project allows the company to find more meaning in its' data to help negotiate better contracts and identify products that are doing well or declining on a global basis. 

From the intelligence perspective, the National Research Council ranked data mining technology with antibiotics, vaccines, imaging and other technologies in the fight against terrorism. Text mining, video mining, audio phone mining and e-mail mining could all become important in the area of homeland defense (Roberts-Witt, 2002).

Roberts-Witt, S. L. 2001. Gold diggers: Let customers and partners mine your data using new e-business intelligence tools. It could turn into a gold rush. PC Magazine (February, 20): ibiz 6-ibiz 10.

Roberts-Witt, S. L. 2002. Data mining: What lies beneath? Finding patterns in customer behavior can deliver profitable insights into your business. PC Magazine (November, 19): iBiz 1-6. 

For more on data mining see Calderon, T. G., J. J. Cheh and I. Kim. 2003. How large corporations use data mining to create value. Management Accounting Quarterly (Winter): 1-11.

	Web maaw.info