Data mining technology has recently taken on a new meaning. Although some consider data mining to be vague, ambiguous and redundant - as it overlaps with data profiling, data warehousing, and even such approaches to data analysis as online analytical processing (OLAP) and enterprise analytic applications - data mining has evolved into another category altogether.

Data mining has been regrouped into the "predictive analytics" category. The main differentiators between predictive analytics, data warehousing and classic data mining, are summarized in the following table:

Data Warehousing	Classic Data Mining	Predictive Analytics
Query and reporting functions (SQL)	Statistical analysis	Prescriptive algorithms
Static perspective	Continuous changes	Also discontinuous changes
Describe the present and past	Predict the past	Predict the future

The above differentiators can be illustrated by the following example. The process of sifting through large volumes of billing data to identify a small batch of billing errors is commonly known as classic data mining. However, this process is descriptive, not prescriptive. When a model can predict errors based on the correlation of variables, then the analysis is able to recommend steps that can be taken to resolve any potential problem before they impact business performance - this process is data mining for predictive analytics.

Another example of a differentiator can be viewed by the predictive value of data mining. Market trend analysis, as performed in data warehousing, OLAP and analytic applications, often asks what customers are buying or using (product or service), and then infers a straight line from the past into the future, extrapolating a trend, also known as data mining.

This basically "predicts the past" and then projects into the future; thus, the prediction is not really in the analysis. Data mining in this case is only able to envision continuous change - extending the trend from past to future. Predictive analytics would be able to generate scores from models that envision discontinuous changes - not only peaks and valleys, but cliffs and crevasses.

Clearly, predictive analytics is a much more effective tool than data mining at tapping into future trends along with taking a proactive role with regards to generating new and insightful information for businesses.