Abstract
In contrast to the Industrial Revolution, the Digital Revolution is happening much more quickly. For example, in 1946, the world’s first programmable computer, the Electronic Numerical Integrator and Computer (ENIAC), stood 10 feet tall, stretched 150 feet wide, cost millions of dollars, and could execute up to 5,000 operations per second. Twenty- five years later, Intel packed 12 times ENIAC’s processing power into a 12–square-millimeter chip. Today’s personal computers with Pentium processors perform in excess of 400 million instructions per second. Database systems, a subfield of computer science, has also met with notable accelerated advances. A major strength of database systems is their ability to store volumes of complex, hierarchical, heterogeneous, and time-variant data and to provide rapid access to information while correctly capturing and reflecting database updates. Together with the advances in database systems, our relationship with data has evolved from the prerelational and relational period to the data-warehouse period. Today, we are in the knowledge-discovery and data-mining (KDDM) period where the emphasis is not so much on identifying ways to store data or on consolidating and aggregating data to provide a single, unified perspective. Rather, the emphasis of KDDM is on sifting through large volumes of historical data for new and valuable information that will lead to competitive advantage. The evolution to KDDM is natural since our capabilities to produce, collect, and store information have grown exponentially. Debit cards, electronic banking, e-commerce transactions, the widespread introduction of bar codes for commercial products, and advances in both mobile technology and remote sensing data-capture devices have all contributed to the mountains of data stored in business, government, and academic databases. Traditional analytical techniques, especially standard query and reporting and online analytical processing, are ineffective in situations involving large amounts of data and where the exact nature of information one wishes to extract is uncertain. Data mining has thus emerged as a class of analytical techniques that go beyond statistics and that aim at examining large quantities of data; data mining is clearly relevant for the current KDDM period. According to Hirji (2001), data mining is the analysis and nontrivial extraction of data from databases for the purpose of discovering new and valuable information, in the form of patterns and rules, from relationships between data elements. Data mining is receiving widespread attention in the academic and public press literature (Berry & Linoff, 2000; Fayyad, Piatetsky-Shapiro, & Smyth, 1996; Kohavi, Rothleder, & Simoudis, 2002; Newton, Kendziorski, Richmond, & Blattner, 2001; Venter, Adams, & Myers, 2001; Zhang, Wang, Ravindranathan, & Miles, 2002), and case studies and anecdotal evidence to date suggest that organizations are increasingly investigating the potential of data-mining technology to deliver competitive advantage.
TopIntroduction
In contrast to the Industrial Revolution, the Digital Revolution is happening much more quickly. For example, in 1946, the world’s first programmable computer, the Electronic Numerical Integrator and Computer (ENIAC), stood 10 feet tall, stretched 150 feet wide, cost millions of dollars, and could execute up to 5,000 operations per second. Twenty-five years later, Intel packed 12 times ENIAC’s processing power into a 12–square-millimeter chip. Today’s personal computers with Pentium processors perform in excess of 400 million instructions per second. Database systems, a subfield of computer science, has also met with notable accelerated advances. A major strength of database systems is their ability to store volumes of complex, hierarchical, heterogeneous, and time-variant data and to provide rapid access to information while correctly capturing and reflecting database updates.
Together with the advances in database systems, our relationship with data has evolved from the prerelational and relational period to the data-warehouse period. Today, we are in the knowledge-discovery and data-mining (KDDM) period where the emphasis is not so much on identifying ways to store data or on consolidating and aggregating data to provide a single, unified perspective. Rather, the emphasis of KDDM is on sifting through large volumes of historical data for new and valuable information that will lead to competitive advantage. The evolution to KDDM is natural since our capabilities to produce, collect, and store information have grown exponentially. Debit cards, electronic banking, e-commerce transactions, the widespread introduction of bar codes for commercial products, and advances in both mobile technology and remote sensing data-capture devices have all contributed to the mountains of data stored in business, government, and academic databases. Traditional analytical techniques, especially standard query and reporting and online analytical processing, are ineffective in situations involving large amounts of data and where the exact nature of information one wishes to extract is uncertain.
Data mining has thus emerged as a class of analytical techniques that go beyond statistics and that aim at examining large quantities of data; data mining is clearly relevant for the current KDDM period. According to Hirji (2001), data mining is the analysis and nontrivial extraction of data from databases for the purpose of discovering new and valuable information, in the form of patterns and rules, from relationships between data elements. Data mining is receiving widespread attention in the academic and public press literature (Berry & Linoff, 2000; Fayyad, Piatetsky-Shapiro, & Smyth, 1996; Kohavi, Rothleder, & Simoudis, 2002; Newton, Kendziorski, Richmond, & Blattner, 2001; Venter, Adams, & Myers, 2001; Zhang, Wang, Ravindranathan, & Miles, 2002), and case studies and anecdotal evidence to date suggest that organizations are increasingly investigating the potential of data-mining technology to deliver competitive advantage.
As a multidisciplinary field, data mining draws from many diverse areas such as artificial intelligence, database theory, data visualization, marketing, mathematics, operations research, pattern recognition, and statistics. Research into data mining has thus far focused on developing new algorithms and tools (Dehaspe & Toivonen, 1999; Deutsch, 2003; Jiang, Pei, & Zhang, 2003; Lee, Stolfo, & Mok, 2000; Washio & Motoda, 2003) and on identifying future application areas (Alizadeh et al., 2000; Li, Li, Zhu, & Ogihara, 2002; Page & Craven, 2003; Spangler, May, & Vargas, 1999). As a relatively new field of study, it is not surprising that data-mining research is not equally well developed in all areas. To date, no theory-based process model of data mining has emerged. The lack of a formal process model to guide the data-mining effort as well as identification of relevant factors that contribute to effectiveness is becoming more critical as data-mining interest and deployment intensifies. The emphasis of this article is to present a process for executing data-mining projects.
Key Terms in this Chapter
Data Mining: Analysis and nontrivial extraction of data from databases for the purpose of discovering new and valuable information, in the form of patterns and rules, from relationships between data elements.
Cluster: Subset of data records; the goal of clustering is to partition a database into clusters of similar records such that records that share a number of properties are considered to be homogeneous.
Operational Data Store: An integrated repository of transaction-processing systems that uses data-warehouse concepts to provide “clean” data in support of day-to-day operations of a business.
Data Mart: Scaled-down version of an enterprise-wide data warehouse that is created for the purpose of supporting the analytical requirements of a specific business segment or department.
Information: Interpreted symbols and symbol structures that reduce both uncertainty and equivocality over a defined period of time.
Data Warehouse: A platform consisting of a repository of selected information drawn from remote databases or other information sources, which forms the infrastructural basis for supporting business decision making.
Knowledge: Information combined with experience, context, interpretation, and reflection.