A Brief Data Mining History

Data mining history started about 30 to 40 years ago but it was not called that then. It started off as statistical analysis, promoted by two companies SAS and SPSS.

Statistics with regression analysis, standard distribution/deviation/variance, cluster analysis, confidence intervals is still important but today new techniques add greatly to the power of the statistics routines.

These new methods such as fuzzy logic, heuristics and neural networks were arriving on the scene in the 1980's. These could be classified into two groups - artificial intelligence and machine learning. As the 80's progressed computing power enabled more powerful and large analyses.

First workshops on knowledge discovery in databases (KDD another name for data mining) in the early 1990's. The number of conferences is now increasing all the time. In summary could be said that data mining had three sources or roots

• Statistics
• Artificial Intelligence using human-thought-like and nature like processing e.g. genetic algoritms
• Machine Learning where you let computer programs learn about data they study e.g. neural networks, pattern recognition

The science is becoming established with more products and services are coming onto the market and today being applied to a wide range of areas such as:

• Financial Industry, Banks, Businesses, E-commerce
• Retail and Marketing
• Sports and Entertainment
• Astronomy

One could say that data mining as it is defined today is about 10 to 15 years old.

Go to Top of Data Mining History page

Back To 'What is Data Mining' page

Back to 'Business Intelligence' Home Page