EXIN DAF Certification Sample Questions

01. Why is aesthetic design important?
a) It enhances machine learning techniques.
b) It facilitates natural language processing (NLP).
c) It focuses on regression analysis models.
d) It improves the usability of data visualization.

02. A task in natural language processing (NLP) involves identifying important entities mentioned in text, such as name, location, or an activity. Which NLP task is this?
a) Class identification
b) Named entity recognition
c) Sentiment analysis
d) Stemming

03. To get a better insight of the prices of houses sold in different quarters of a city, a real-estate broker wants to use a heatmap. What does this heatmap show?
a) A plan of the city with levels of house prices represented in colors
b) A plan of the city with sold houses and the selling price per house
c) A table with average house prices in the past year per quarter sorted per average price
d) A table with prices of houses sold in the past year ordered by price

04. What data visualization tool has the look and feel of Microsoft Excel?
a) Data Wrapper
b) Google Charts
c) Power BI
d) Tableau

05. What is a key difference between association analysis and sequence mining?
a) Association analysis applies the generalized sequential patterns (GSP) technique, while sequence mining applies Apriori.
b) Association analysis disregards the order in which items appear, while sequence mining considers it.
c) Association analysis uses a confidence level to aid decision-making, while sequence mining is supervised learning.
d) Association analysis works better on large datasets, while sequence mining is best suited for small datasets.

06. Which type of plot is used to display the spread and skewness of a dataset?
a) Box plot
b) Rug plot
c) Scatterplot
d) Violin plot

07. In what case should descriptive analysis be used?
a) When a data set cannot be analyzed easily
b) When limited information is available
c) When the retrieved data is very detailed
d) When there are gaps in record keeping

08. Why is it important to distinguish between discrete and continuous variables?
a) Because it is important to define the conceptual data model
b) Because it helps select the algorithms suitable for the variables
c) Because only discrete variables can be aggregated with other variables
d) Because relational databases can only store continuous variables

09. A company has a large dataset of shirts sales. The staff wants to better understand the figures and the data analyst is considering whether cluster analysis could offer any insight. How does k-means clustering give a better understanding of the sales figures?
a) By clustering data in predefined groupings
b) By describing unexpected relationships between clusters
c) By explaining the role of centroids
d) By providing a new way of grouping customers

10. Which graphic technique is typically used when delivering data to an external audience?
a) Explanatory
b) Expansionary
c) Explicatory
d) Exploratory