Predictive Intelligence

Question 1

What is Predictive Intelligence?

Answer 1

an interface by which you can train models using the ServiceNow AI Platform.

Question 2

Provide input/output pairs, so the computer can generate a rule that maps between the two. The output rule is often referred to as a model or solution.

Answer 2

Supervised Learning/Training

Question 3

Provide raw data, allow the computer to identify structure within the input data set. The output is referred to as a model or solution.

Answer 3

Unsupervised Learning/Training

Question 4

What attempts to explain the behavior of a target attribute, as a function of a set of independent input attributes?

Answer 4

Classification

Question 5

What attempts to predict a numeric value for a target, as a function of a set of independent input attributes?

Answer 5

Regression

Question 6

What is clustering?

Answer 6

Clustering groups similar records into into clusters so you can address them collectively or identify patterns.

Question 7

What is similarity?

Answer 7

Given a lookup set of raw data, predict similarity (output) between a given set (input) and the raw data.

Question 8

A system designed to perform tasks, usually requiring a level of human intelligence.

Answer 8

Artificial Intelligence (AI)

Question 9

A subset of AI that provides the ability to improve from experience. This action is done by using algorithms, mathematics, and statistics to create models that make predictions/decisions.

Answer 9

Machine Learning (ML)

Question 10

What roles are associated with Predictive Intelligence?

Answer 10

[ml_admin] & [ml_report_user]

Question 11

The predictive model that is generated as the output of training (supervised or unsupervised) using the training data set (output of solution definition).

Answer 11

Solution

Question 12

Given a set of correlated inputs/outputs, the solution generated will also predict an output based on user input.

Answer 12

Classification

Question 13

Given raw data (lookup set), the solution generated will predict similarity between a given input (example set) and the raw data

Answer 13

Similarity

Question 14

A collection of all the words and phrases that the machine can use for that particular solution to compare rows of data based on textual similarity.

Answer 14

Word Corpus

Question 15

Given raw data, the solution generated will generate a structure across the input data set. Each set of similar records is grouped to address them collectively or identify patterns that were not detected before.

Answer 15

Cluster

Question 16

The proportion of positive identifications that is actually correct. Calculated as the number of true positives divided by the sum of true positives and false positives.

Answer 16

Precision

Question 17

The aggregate percentage of records that receive a prediction.

Answer 17

Coverage

Question 18

To predict field values, which type of solution should you create?

Answer 18

Classification

Question 19

To group similar records into clusters so you can address them collectively or identify patterns, which type of solution should be created?

Answer 19

Clustering

Question 20

Predictive Intelligence offers out-of-the-box solutions for which applications?

Answer 20

ITSM, CSM, HR, and Event Management

Question 21

At a minimum, which role is required to manage Predictive Intelligence solutions?

Answer 21

[ml_admin]

Question 22

T | F: Regression is a machine-learning framework that can be trained with historical data to predict numeric outputs, such as a temperature or a stock price.

Answer 22

True

Question 23

To surface similar tasks and content to predict new major issues and recommend critical actions, which type of solution should you create?

Answer 23

Similarity

Question 24

When implementing PI, how many historical records does ServiceNow recommend you have?

Answer 24

Between 30,000 and 300,000.

Question 25

This setting groups together points that are close to each other based on a distance measurement and a minimum number of points. It also marks as outliers the point that are in low-density regions.

Answer 25

DBSCAN

Question 26

T | F: DBSCAN is only available for similarity solutions.

Answer 26

False: It is available for Clustering solutions only.

Question 27

This setting evaluates how ‘important’ a word is to a document in the document set or word corpus. The setting is available for Classification and Similarity solutions.

Answer 27

TF-IDF

Question 28

T | F: TF-IDF is available for Clustering and Similarity solutions.

Answer 28

False - It is available for Classification and Similarity solutions.

Question 29

What is the minimum number of required records for Classification solution training?

Answer 29

10,000

Question 30

T | F: Clustering solutions can reuse an existing word corpus.

Answer 30

True

Question 31

T | F: Clustering solutions groups data based on similarity.

Answer 31

True

Question 32

T | F: Clustering solutions generate classes.

Answer 32

False

Question 33

T | F: Clustering solutions does not support multiple languages.

Answer 33

False

Question 34

What is the purpose of a word corpus?

Answer 34

The word corpus is the vocabulary the system uses to compare textual similarity between records.

Question 35

What is the maximum classes a classification solution can support?

Answer 35

There is no limitation on the amount of classes a classification solution can support.

Question 36

To predict field values, which type of solution should be created?

Answer 36

Classification

Question 37

For classification solutions, how many possible outputs can a single solution include?

Answer 37

A solution can only have one output.

Question 38

How do you preserve solutions during a system clone?

Answer 38

There is a system property that can be set to true to preserve your solutions.