Objective 7.1 Report Findings CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 7)

Questions 31–35

1. 31foundation · easy

   Which of the following is a common technique used to visualize feature importance?

   • AConfusion matrix
   • BVariable importance plot
   • CLearning curve
   • DROC curve
   Reveal Solution Discussion Select an answer first
2. 32foundation · easy

   What is the primary goal of deriving insights from model findings?

   • ATo replace the need for stakeholder communication
   • BTo increase the complexity of the model
   • CTo ensure the model is overfitted to the training data
   • DTo inform decision-making with actionable recommendations
   Reveal Solution Discussion Select an answer first
4. 33foundation · easy

   What is the main purpose of using CSS in a web application that presents model results?

   • ATo add interactivity and handle user clicks
   • BTo define the structure of the web page
   • CTo store and retrieve data from a database
   • DTo control the visual presentation, such as layout, colors, and fonts
   Reveal Solution Discussion Select an answer first
5. 34foundation · easy

   Which of the following is an example of an actionable insight derived from a model's findings?

   • AThe model's accuracy is 85%
   • BCustomers with high usage are more likely to churn, so offer them a retention discount
   • CThe model uses a random forest algorithm
   • DThe dataset contains 10,000 rows
   Reveal Solution Discussion Select an answer first
6. 35application · medium

   A data science team has trained a churn prediction model and needs to show business stakeholders a quick, interactive demo. The team has no dedicated front-end developers and needs to stand up a minimal web page that accepts a customer ID, calls the model, and displays the churn probability. The solution must be deployable on a single server with minimal configuration. Which approach best meets these requirements?

   • ACreate a Django project with a full admin interface, database models, and a custom app to handle the prediction form.
   • BBuild a Flask app with a single HTML template and a form that posts to a prediction endpoint, styled with a small CSS file.
   • CWrite a static HTML page that uses JavaScript to load the model directly in the browser and compute predictions client-side.
   • DDeploy a Jupyter Notebook with ipywidgets and share the notebook URL with stakeholders for them to run predictions.
   Reveal Solution Discussion Select an answer first