Hands-On Exercise: Build a Defect Prediction System CT-AI Practice Questions (Page 2)

Questions 6–10

1. 6application · medium

   A QA team wants to build a defect prediction model for a legacy Java application. They have access to the version control history, issue tracker, and code coverage reports. Which data collection approach best supports the goal of predicting which modules are likely to contain defects in the next release?

   • ACollect static code metrics (e.g., cyclomatic complexity, lines of code) and historical defect counts per module from the issue tracker, then align them by release.
   • BUse the issue tracker to count all reported issues, including feature requests and documentation tasks, as defect labels.
   • CCollect only the number of lines of code changed per developer per day from version control, ignoring defect data.
   • DExport the latest code coverage report and use it as the sole feature, assuming high coverage means low defects.
   Reveal Solution Discussion Select an answer first
2. 7application · medium

   A defect prediction model has been deployed. The QA team wants to integrate the predictions into their testing process. Which approach is most effective?

   • AUse the model only to generate reports for management, not for testing decisions.
   • BUse the model's predictions to prioritize test case execution, focusing on high-risk modules first.
   • CReplace all manual testing with the model's predictions.
   • DIgnore the model's predictions and continue with the existing testing process.
   Reveal Solution Discussion Select an answer first
4. 8foundation · easy

   What is a key consideration when integrating a defect prediction model into the testing process?

   • AThe model should be used only once and then discarded
   • BThe model's output should be kept confidential from the testing team
   • CThe model's predictions should be reviewed by testers and combined with their domain knowledge
   • DThe model should replace all manual testing activities
   Reveal Solution Discussion Select an answer first
5. 9foundation · easy

   Which of the following is an example of feature engineering for a defect prediction model?

   • ASplitting the dataset into training and testing sets
   • BCreating a new feature that counts the number of times a module has been changed
   • CReplacing missing values with the mean of the column
   • DRemoving features that have missing values
   Reveal Solution Discussion Select an answer first
6. 10foundation · easy

   Which of the following is an example of a software metric that would be relevant for defect prediction?

   • AThe number of lines of code in a module
   • BThe color scheme of the user interface
   • CThe version number of the operating system
   • DThe name of the developer who wrote the code
   Reveal Solution Discussion Select an answer first