Book Chapter Draft
Gary M. Weiss and Brian D. Davison
Advances in computer technology have resulted in enormous amounts of data being recorded and stored. Much of this data, however, remains unanalyzed even though useful knowledge is unquestionably buried within. Conventional statistical techniques are often not sufficient to unlock this knowledge because these methods: may be too weak/shallow, may make assumptions about the data that do not hold, are unable to handle massive datasets, are not able to handle the data types (which is often non-numerical), or because the methods place too much of the workload on the analyst. Data mining, which utilizes computational methods (i.e., computer algorithms) to unlock the knowledge in data, provides at least a partial solution to these problems. Data mining methods have continued to gain in popularity over the past decade and a basic understanding of data mining and its capabilities is essential for knowledge workers in today's information-based society. In this chapter we provide an overview of data mining. We describe what data mining is, what types of problems it can address, and, at a very high level, how data mining methods operate.
Reference: Gary M. Weiss and Brian D. Davison (2010). Data Mining. In H. Bidgoli (ed.), Handbook of Technology Management, John Wiley and Sons, Volume II, Chapter 39, January 2010.
Back to Brian Davison's publications