Identify Common Machine Learning Techniques AI-900 Practice Questions (Page 2)

Questions 6–10

1. 6expert · hard

   A customer support system wants to automatically categorize support tickets into 'billing', 'technical', or 'general'. They also want to predict the time to resolve each ticket. Which approach should they use?

   • AUse a classification model for ticket category, and a regression model for resolution time.
   • BUse a regression model for ticket category, and a classification model for resolution time.
   • CUse a clustering model for ticket category, and a regression model for resolution time.
   • DUse a transformer model for both tasks.
   Reveal Solution Discussion Select an answer first
2. 7application · medium

   A bank wants to approve or reject loan applications based on applicant data. They also want to estimate the probability of default for each applicant. Which approach should they use?

   • AClustering to approve/reject, and regression to estimate default probability.
   • BClassification to approve/reject, and regression to estimate default probability.
   • CA transformer model to approve/reject and estimate default probability.
   • DRegression to approve/reject, and classification to estimate default probability.
   Reveal Solution Discussion Select an answer first
4. 8expert · hard

   A retail chain wants to segment its stores into groups based on sales patterns, foot traffic, and product mix. They do not have predefined segments and want to discover natural groupings. However, they also want to predict next month's sales for each store. Which approach should they use?

   • AUse clustering to discover store segments, then train a regression model for each segment to predict sales.
   • BUse regression to predict sales, then use the residuals to cluster stores.
   • CUse classification to assign stores to predefined segments, then use regression to predict sales.
   • DUse a transformer to generate a text summary of each store's performance.
   Reveal Solution Discussion Select an answer first
5. 9foundation · easy

   A marketing team wants to divide its customers into groups based on purchasing behavior, but they do not have predefined customer segments. Which machine learning technique should they use?

   • ARegression
   • BClassification
   • CReinforcement learning
   • DClustering
   Reveal Solution Discussion Select an answer first
6. 10expert · hard

   A legal firm wants to automatically classify legal documents into categories such as 'contract', 'brief', or 'memo', and also extract key entities like dates and party names. The documents are lengthy and require understanding of context. Which approach should they use?

   • AUse a Transformer model fine-tuned for document classification and named entity recognition.
   • BUse a simple keyword-based system.
   • CUse a clustering algorithm to group similar documents.
   • DUse a regression model to predict document length.
   Reveal Solution Discussion Select an answer first