4.1 Explain AI’s Role in Exploratory Data Analysis (EDA) AI-TECHNICAL-PRACTITIONER Practice Questions (Page 3)

Questions 11–15

1. 11application · medium

   A data analyst receives a large, unfamiliar dataset with hundreds of columns and mixed data types. The analyst needs to quickly understand the overall structure, spot obvious data quality issues, and get a first look at potential relationships before diving into detailed analysis. Which approach best leverages AI for this initial exploration?

   • AManually review each column's values and create scatter plots for every pair of variables.
   • BUse an AI-powered profiling tool to automatically summarize distributions, detect anomalies, and generate relevant visualizations.
   • CAsk a domain expert to list all possible relationships and then verify each one manually.
   • DImmediately train a predictive model to see which columns are most important, skipping the profiling step.
   Reveal Solution Discussion Select an answer first
2. 12application · medium

   A healthcare analyst is preparing a patient outcomes dataset that contains missing blood pressure readings and some noisy sensor data. The analyst wants to use AI to handle these issues before running further analysis. Which approach best aligns with AI's role in EDA for this scenario?

   • AManually estimate each missing value by looking at other patients with similar conditions.
   • BDelete all records with missing blood pressure readings and ignore the noisy sensor data.
   • CUse an AI-based imputation method that estimates missing values from other patient features, and apply a filtering algorithm to smooth out sensor noise.
   • DReplace missing values with the number zero and leave the noisy data unchanged.
   Reveal Solution Discussion Select an answer first
4. 13foundation · easy

   How does AI automate visualization in EDA?

   • ABy replacing all visualizations with textual summaries
   • BBy requiring the analyst to specify every chart type and parameter
   • CBy generating charts and plots that highlight trends and outliers without manual specification
   • DBy creating static images that cannot be updated
   Reveal Solution Discussion Select an answer first
5. 14expert · hard

   A data science team is using an AI tool that automatically generates hypotheses about customer churn. The tool suggests that 'customers who contact support more than three times are more likely to churn.' The team wants to use this hypothesis to design a retention campaign. What is the most appropriate course of action?

   • AReject the hypothesis because AI-generated hypotheses are often biased.
   • BValidate the hypothesis using historical data and statistical significance testing before launching the campaign.
   • CAsk the AI tool to automatically implement the campaign without human review.
   • DImmediately launch the campaign targeting customers with more than three support contacts.
   Reveal Solution Discussion Select an answer first
6. 15foundation · easy

   Which AI technique is commonly used to group similar data points during EDA?

   • AClustering
   • BRegression
   • CReinforcement learning
   • DClassification
   Reveal Solution Discussion Select an answer first