Exam 10: Business Intelligence Systems

________ is the application of statistical techniques to find patterns and relationships among data for classification and prediction.

Because of a phenomenon called the curse of measurability,the more attributes there are,the easier it is to build a model that fits the sample data but that is worthless as a predictor.

Cluster analysis is used to identify groups of entities that have similar characteristics.

In market-basket terminology,the conditional probability estimate of buying an item given you bought another one is called the ________.

What is an RFM analysis?

Differentiate between unsupervised and supervised data-mining.

Wrong granularity implies that data could be too fine or too coarse.

In most cases,data-mining tools are used to make assessments.

With a(n)________ you can subscribe to content sources and be notified when they have been changed.

In market-basket terminology,the ratio of confidence to the base probability of buying an item is the ________.

The viewer of the report can change the OLAP report's format.Which term implies this capability?

Though they are difficult and expensive to develop,the low maintenance cost of expert systems makes them an attractive business proposition.

DBMS servers are used to create OLAP reports from very large databases.

A(n)________ notifies the user of an exceptional event,such as a dramatic fall in a stock price.

Metadata describes the data.

________ attempt to capture human expertise and put it into a format that can be used by nonexperts.

Portal servers are like Web servers except that they do not have a customizable user interface.

OLAP stands for Organizational Lead Analysis Program and is used extensively to generate reports for marketing and sales.

Which of the following is used by businesses to process data in order to produce patterns,relationships,and other forms of information and to deliver that information on a timely basis to users who need it?

Because of a phenomenon called the ________,the more attributes there are,the easier it is to build a model that fits the sample data but that is worthless as a predictor.