10.__________ is a data mining technique which helps to define a set of rules to
ID: 3721271 • Letter: 1
Question
10.__________ is a data mining technique which helps to define a set of rules to be used in making decisions based on training and testing data sets.
11.When the data mining technique in the previous question is used with a finite set of variables it generates a ___________________________.
12.When the data mining technique in question 10 is used with a continuous set of variables it generates a ___________________________.
13.__________ is a data mining technique used to determine patterns in a data set such as when product A is purchased it is likely that product B will also be purchased.
14.In the previous data mining method, __________ measure of the performance of an association rule at predicting or classifying cases as having an enhanced response, measured against a random targeting model.
15.What are the two distinct steps that one needs to perform when developing a data mining model in SAP? ____________________________ and _____________________________
16._____________ is a multidimensional data structure that allows users to quickly retrieve the sought after results in a ‘BI’ environment.
17.__________________ is a mathematical model which optimizes the solution of resource allocation problems under which all the relationships are linear.
18.In order to perform text mining, analysts must first apply ________________ to unstructured data.
19.__________ data are expressed in numbers (continuous or discrete) and represent a value. __________ data are categorical, and while they may be expressed in numbers as well, these numbers would only be ordinal or nominal.
20.Prescriptive analytics are primarily about these two techniques: ____________________ and
_________________.
21.What four characteristics separate Big Data from other BI data: ___________________,
___________________, ___________________ and ___________________.
22.__________ is a Big Data distributed file system built on many inexpensive servers that provide redundancy and quick response to queries based on massive volumes of data.
23.__________ is a programming model that allows a programmer to write a program which gets processed on the many inexpensive distributed servers and the results are returned and accumulated for the user.
24.__________ is a new database model for storing and processing discrete multi-structured Big Data for end users or automated Big Data applications.
25.__________ is a new Big Data position in which the employee needs to be skilled at statistics, technology, business and communications.
Explanation / Answer
10. Rule based classification is a data mining technique which helps to define a set of rules to be used in making decisions based on training and testing data sets.
It makes use of IF-THEN rules of classification , The rule is expressed as,
IF condition THEN conclusion
11. When the data mining technique in the previous question is used with a finite set of variables it generates a Categorical data.
It consists of a finite number of categories or distinct groups.
12. When the data mining technique in question 10 is used with a continuous set of variables it generates a Continuous data.
It consists of infinite number of values between any two values.
13. In the previous data mining method, Lift measure of the performance of an association rule at predicting or classifying cases as having an enhanced response, measured against a random targeting model.
Lift is the ratio of the values target response and average response.
Related Questions
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.