Objective 4.2 Train Models CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 6)

Questions 26–30

1. 26application · easy

   A data scientist is training a linear regression model using gradient descent. The loss function is decreasing very slowly, and the model is taking too long to converge. Which adjustment is most likely to speed up convergence?

   • AIncrease the learning rate
   • BDecrease the learning rate
   • CUse a different loss function
   • DIncrease the number of iterations
   Reveal Solution Discussion Select an answer first
2. 27application · medium

   A retail company wants to forecast monthly sales for the next year based on historical sales data. The data shows a clear seasonal pattern and trend. Which model is most appropriate for this time series forecasting task?

   • AARIMA
   • BRandom forest regression
   • CK-means clustering
   • DLinear regression
   Reveal Solution Discussion Select an answer first
4. 28foundation · easy

   What is a major drawback of grid search?

   • AIt always finds the global optimum
   • BIt requires a GPU to run
   • CIt can be computationally expensive as the number of hyperparameters grows
   • DIt only works for linear models
   Reveal Solution Discussion Select an answer first
5. 29application · medium

   A real estate analytics firm needs to predict the sale price of residential homes based on square footage, number of bedrooms, lot size, and neighborhood. The target variable is continuous, and the relationship between the predictors and the target is approximately linear. The team needs a model that is easy to interpret for client presentations. Which model should they select?

   • AXGBoost regression
   • BLinear regression
   • CRandom forest regression
   • DK-means clustering
   Reveal Solution Discussion Select an answer first
6. 30foundation · easy

   What is the key difference between XGBoost and a random forest for classification?

   • AXGBoost is only for regression, while random forest is only for classification
   • BXGBoost builds trees sequentially, while random forest builds trees independently
   • CXGBoost uses a single tree, while random forest uses many trees
   • DXGBoost requires feature scaling, while random forest does not
   Reveal Solution Discussion Select an answer first