C_PAII10_35問題集、SAP実際の試験問題

質問 1

The importance of a category depends on both its difference to the
target category mean and the number of represented cases. High importance can result from any of the following:
Note: There are 3 correct answers to this question.

A. A combination of both

B. A minor discrepancy combined with a large number of records in the category

C. A high discrepancy between the category and the mean of the target category of the target variable

D. recise scheduling of main industrialization tasks

正解: A,B,C

質問 2

Predictive Power, Prediction Confidence and Model Graphs On the model graph plot:
Note: There are 2 correct answers to this question.

A. Of the validation dataset of the perfect model and that of the random model". As the curve of the generated model approaches the curve of the perfect model, the value of the predictive power approaches 1.

B. Produce deep analysis of the data using different visualization
techniques, such as scatter matrix charts, parallel coordinates, cluster charts, and decision trees.

C. Of the training and validation datasets the training dataset and that of the validation dataset "divided by "the area found between the curve of the perfect model and that of the random model"

正解: A,C

質問 3

Depending upon your profile and your area of expertise,
you may be more familiar with one of the following terms to
refer to target variables:
Note: There are 3 correct answers to this question.

A. Dependent variables,

B. Variables to be explained,

C. Output variables.

D. User activity monitoring and logging is possible and activated by default.

正解: A,B,C

質問 4

There are three ways to define a variable structure:
Note: There are 3 correct answers to this question.

A. by importing the structure from an existing model.

B. if the user running SAP Predictive Analy

C. by building a new structure from scratch.

D. by first extracting the categories from the variable statistics,
then editing or validating the suggested structure.

正解: A,D

質問 5

In the Random Forest algorithm, each regressor and
classifier is built on a bootstrapped sample. At each split, a
random sample of m features is considered for splitting from
a total of M features. What is the default setting for m?
Note: There are 1 correct answers to this question.

A. m = sqrt(M) for regression and sqrt (M) for classification

B. m = sqrt(M) for regression and M/3 for classification

C. m = M/3 for regression and M/3 for classification

D. m = M/3 for regression and sqrt (m) for classification

正解: D

質問 6

Once your business issue has been identified and formulated, you need to have data on hand that will permit an answer to be found. In order for your data to be usable by the application, the following five conditions must be met:
Note: There are 5 correct answers to this question.

A. Your data must be presented in the form of a single table of data , except in instances where you are using Event Logging or Sequence Coding features of Data Manager.

B. Server instances are going to be started with a different system account than the authenticated server.

C. You must have a sufficiently large volume of data to be able to build a valid model, that is, in order for the model to be both relevant and robust. An analytical model that is generated from a dataset of 50 lines may have low generalization capacity, and contain low informative value. We can advise you on the issues of data volume.

D. The target variable must be known for each observation of the training dataset. To express this another way, no target variable values may be missing over the range of the entire training dataset.

E. Your dataset must contain a target variable, that will allow you to express your business issue within the application.

F. The data source format must be supported by the application.

正解: A,C,D,E,F

質問 7

On the plot, for each type of model, the curves represent:
Note: There are 2 correct answers to this question.

A. When the target is continuous, the predicted value or score on
the X axis In respect with the actual value or target value or
target (on the Y axis)

B. A valid SAP Predictive Analytics License

C. When the target is nominal, the realizable profit (on the Y axis ) as a function of the ratio o f the observations correctly selected as targets relative to the entire initial dataset (on the X axis)

正解: A,C

質問 8

Obtaining a better model is achieved by:
Note: There are 3 correct answers to this question.

A. Improving both the predictive power and he prediction
confidence of the model.

B. Improving the predictive power of the model, or

C. System authentication is to be used through Pluggable
Authentication Module (PAM). Access to Linux System
account password required root privileges.

D. Improving the prediction confidence of the model, or

正解: B,D

SAP Certified Application Associate - SAP Predictive Analytics - C_PAII10_35 模擬練習