BUSINESS DATA ANALYTICS EXAM
QUESTIONS WITH COMPLETE ANSWERS
1. Descriptive Analytics phase: - ANS-Purpose: involves summarizing and presenting a comprehensive
view of historical data to provide insights into WHAT has happened in the past. It aims to describe and
understand patterns, trends, and key features of the data.
Methods: Techniques like summary statistics, data visualization, and reporting are used to present a
clear picture of historical data.
Example: If a retail company analyzes its sales data from the past year to identify best/worst-selling
products, peak sales periods, and customer demographics
2. Diagnostic Analytics phase: - ANS-Purpose: delves deeper into the data to identify relationships and
drivers of observed patterns.it builds on descriptive analytics by digging into WHY certain events
occurred. It involves analyzing historical data to understand the reasons behind specific outcomes,
patterns, trends
Methods: Comparative analysis, root cause analysis, and correlation analysis are common diagnostic
analytics methods.
Example: A company notices a sudden drop in website traffic and employs diagnostic analytics to
investigate the possible reasons, discovering that the decrease is linked to a recent change in the
website's user interface.
Identifying Anomalies/Outliers phase: - ANS-This is a subset of both descriptive and diagnostic analytics,
focusing on recognizing irregularities or unexpected deviations from typical patterns.
*Anomalies: data points that deviate significantly from the norm.
Often a first step in diagnostic analytics is to look for and identify unusual, unexpected results or
transactions.
Don't immediately assume something is wrong. Verify the data, and if it's indeed an outlier, investigate
why it's different. d/t errors, unusual events, or genuine changes?
Methods: Statistical techniques, machine learning algorithms, and visualizations are employed to detect
anomalies. This process helps highlight data points that might require further investigation to
understand their origins or implications.
, What is required to determine whether a finding is an anomaly or outlier? - ANS-Set an Expectation --
define a threshold that determines what is "normal" for your data. This could be based on past
observations, industry standards, or common expectations. Data points beyond this limit might be
considered outliers.
In practice, these three types of analytics often work together in a cyclical manner. Insights gained from
________ analytics may lead to further investigation using ________ analytics, and the identification of
________ may prompt a revisit of the descriptive and diagnostic analyses.
This process enhances the understanding of data and supports informed decision-making based on a
thorough inspection of historical information. - ANS-descriptive --- > diagnostic --- > anomalies
Diagnostic analytics, descriptive analytics, and identifying anomalies/outliers are three _______
components within the broader field of data analytics, each serving a distinct purpose in the analytical
process. - ANS-interrelated
Predictive Analytics: - ANS-Using statistical algorithms and machine learning techniques to FORECAST
FUTURE OUTCOMES based on historical data. It aims to predict what might happen in the future.
Example: A credit card company might use predictive analytics to assess a customer's likelihood of
defaulting on a payment based on their past spending behavior, credit history, and other relevant
factors.
Prescriptive Analytics: - ANS-Goes beyond predicting future outcomes; it recommends actions to
optimize or improve those outcomes. It leverages data, algorithms, and business rules to provide
actionable insights.
Example: An e-commerce platform uses prescriptive analytics to recommend personalized product
offerings to customers based on their browsing history, preferences, and current trends, aiming to
maximize sales and customer satisfaction.
exploratory business analytics: - ANS-has less focused on predicting future events with statistical
certainty. involves describing past performance, exploring summary performance statistics (data) to
uncover new insights, detect patterns, or relationships, identify anomalies and outliers, and checking
assumptions - often w/o a predefined question.
Example: A retail company may conduct exploratory analytics on its sales data to identify unexpected
trends or correlations. This could involve visualizing the data in various ways and exploring different
variables to gain insights without having a specific question in mind.
confirmatory business analytics: - ANS-involves testing specific hypotheses using statistical methods to
draw conclusions about the data based on a predetermined question or theory. well suited for judging
the likelihood of future events.
Example: A pharmaceutical company may use confirmatory analytics to test the effectiveness of a new
drug. The hypothesis might be that the drug significantly reduces symptoms compared to a placebo. The
QUESTIONS WITH COMPLETE ANSWERS
1. Descriptive Analytics phase: - ANS-Purpose: involves summarizing and presenting a comprehensive
view of historical data to provide insights into WHAT has happened in the past. It aims to describe and
understand patterns, trends, and key features of the data.
Methods: Techniques like summary statistics, data visualization, and reporting are used to present a
clear picture of historical data.
Example: If a retail company analyzes its sales data from the past year to identify best/worst-selling
products, peak sales periods, and customer demographics
2. Diagnostic Analytics phase: - ANS-Purpose: delves deeper into the data to identify relationships and
drivers of observed patterns.it builds on descriptive analytics by digging into WHY certain events
occurred. It involves analyzing historical data to understand the reasons behind specific outcomes,
patterns, trends
Methods: Comparative analysis, root cause analysis, and correlation analysis are common diagnostic
analytics methods.
Example: A company notices a sudden drop in website traffic and employs diagnostic analytics to
investigate the possible reasons, discovering that the decrease is linked to a recent change in the
website's user interface.
Identifying Anomalies/Outliers phase: - ANS-This is a subset of both descriptive and diagnostic analytics,
focusing on recognizing irregularities or unexpected deviations from typical patterns.
*Anomalies: data points that deviate significantly from the norm.
Often a first step in diagnostic analytics is to look for and identify unusual, unexpected results or
transactions.
Don't immediately assume something is wrong. Verify the data, and if it's indeed an outlier, investigate
why it's different. d/t errors, unusual events, or genuine changes?
Methods: Statistical techniques, machine learning algorithms, and visualizations are employed to detect
anomalies. This process helps highlight data points that might require further investigation to
understand their origins or implications.
, What is required to determine whether a finding is an anomaly or outlier? - ANS-Set an Expectation --
define a threshold that determines what is "normal" for your data. This could be based on past
observations, industry standards, or common expectations. Data points beyond this limit might be
considered outliers.
In practice, these three types of analytics often work together in a cyclical manner. Insights gained from
________ analytics may lead to further investigation using ________ analytics, and the identification of
________ may prompt a revisit of the descriptive and diagnostic analyses.
This process enhances the understanding of data and supports informed decision-making based on a
thorough inspection of historical information. - ANS-descriptive --- > diagnostic --- > anomalies
Diagnostic analytics, descriptive analytics, and identifying anomalies/outliers are three _______
components within the broader field of data analytics, each serving a distinct purpose in the analytical
process. - ANS-interrelated
Predictive Analytics: - ANS-Using statistical algorithms and machine learning techniques to FORECAST
FUTURE OUTCOMES based on historical data. It aims to predict what might happen in the future.
Example: A credit card company might use predictive analytics to assess a customer's likelihood of
defaulting on a payment based on their past spending behavior, credit history, and other relevant
factors.
Prescriptive Analytics: - ANS-Goes beyond predicting future outcomes; it recommends actions to
optimize or improve those outcomes. It leverages data, algorithms, and business rules to provide
actionable insights.
Example: An e-commerce platform uses prescriptive analytics to recommend personalized product
offerings to customers based on their browsing history, preferences, and current trends, aiming to
maximize sales and customer satisfaction.
exploratory business analytics: - ANS-has less focused on predicting future events with statistical
certainty. involves describing past performance, exploring summary performance statistics (data) to
uncover new insights, detect patterns, or relationships, identify anomalies and outliers, and checking
assumptions - often w/o a predefined question.
Example: A retail company may conduct exploratory analytics on its sales data to identify unexpected
trends or correlations. This could involve visualizing the data in various ways and exploring different
variables to gain insights without having a specific question in mind.
confirmatory business analytics: - ANS-involves testing specific hypotheses using statistical methods to
draw conclusions about the data based on a predetermined question or theory. well suited for judging
the likelihood of future events.
Example: A pharmaceutical company may use confirmatory analytics to test the effectiveness of a new
drug. The hypothesis might be that the drug significantly reduces symptoms compared to a placebo. The
