A data scientist is evaluating a model for detecting credit card fraud. The dataset is highly imbalanced, with fraud cases being very rare. The model's ROC-AUC is 0.95, but the precision is only 0.10. What does this discrepancy most likely indicate?

The model is overfitting the training data

The model has a high true positive rate but also a high false positive rate at the current threshold

The model is predicting all instances as fraud

The model is underfitting the data

A team is training a neural network for a binary classification task with a 99:1 class imbalance. They decide to use class weights. Which of the following is the most direct effect of applying class weights?

The model's architecture is modified to have more layers

The loss function assigns a higher penalty to misclassifying minority class samples

The model automatically generates synthetic samples for the minority class

The model's learning rate is adjusted to converge faster

A data scientist has a dataset with 10,000 samples of class A and 100 samples of class B. They want to balance the classes using SMOTE. What is the primary advantage of SMOTE over random oversampling?

SMOTE is guaranteed to improve model performance

SMOTE discards majority class samples to balance the dataset

SMOTE creates synthetic samples that are more diverse than simple duplicates

SMOTE reduces the size of the dataset

DatabricksCertified Machine Learning Associate

Domain 3Objective 2

Data Preparation and Imbalance MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 3)

Part of the Section 3: Model Development domain, which makes up ~23% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~8–14 in this domain), expect 2–4 from this objective — we provide 21 practice questions to prepare you well beyond it. (estimate)

21questions here

5free pages

4concepts

Questions 11–15

11application · medium
A data scientist is evaluating a model for detecting credit card fraud. The dataset is highly imbalanced, with fraud cases being very rare. The model's ROC-AUC is 0.95, but the precision is only 0.10. What does this discrepancy most likely indicate?
Select an answer first
12foundation · easy
Which evaluation metric is most appropriate when the cost of false negatives is high and the dataset is imbalanced?
Select an answer first
13foundation · easy
Which resampling technique creates synthetic samples for the minority class by interpolating between existing minority class instances?
Select an answer first
14application · medium
A team is training a neural network for a binary classification task with a 99:1 class imbalance. They decide to use class weights. Which of the following is the most direct effect of applying class weights?
Select an answer first
15application · medium
A data scientist has a dataset with 10,000 samples of class A and 100 samples of class B. They want to balance the classes using SMOTE. What is the primary advantage of SMOTE over random oversampling?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to MACHINE-LEARNING-ASSOCIATE

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “MACHINE-LEARNING-ASSOCIATE” is a trademark of its owner, used for identification only.

Data Preparation and Imbalance MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 3)

Questions 11–15

A data scientist is evaluating a model for detecting credit card fraud. The dataset is highly imbalanced, with fraud cases being very rare. The model's ROC-AUC is 0.95, but the precision is only 0.10. What does this discrepancy most likely indicate?

Which evaluation metric is most appropriate when the cost of false negatives is high and the dataset is imbalanced?

Which resampling technique creates synthetic samples for the minority class by interpolating between existing minority class instances?

A team is training a neural network for a binary classification task with a 99:1 class imbalance. They decide to use class weights. Which of the following is the most direct effect of applying class weights?

A data scientist has a dataset with 10,000 samples of class A and 100 samples of class B. They want to balance the classes using SMOTE. What is the primary advantage of SMOTE over random oversampling?

Keep studying — Section 3: Model Development