Associate Data Practitioner · Free Practice Question Medium
Question 3
A financial analyst needs to create a time-series forecast for quarterly revenue using BigQuery ML. Which model type should they use?
-
A
LINEAR_REG
-
B
ARIMA_PLUS
-
C
KMEANS
-
D
AUTOML_CLASSIFIER
Reveal correct answer
Correct answer: B
Explanation
Option B is CORRECT. ARIMA_PLUS is specifically designed for time-series forecasting in BigQuery ML, making it the ideal choice for predicting quarterly revenue. This model type automatically handles seasonal patterns which are common in quarterly financial data, accounts for trends and cyclic patterns in the time series, includes holiday effects where applicable, and performs automatic hyperparameter tuning to optimize the model.
Option A is INCORRECT. LINEAR_REG can be used for simple trend analysis but doesn't handle the temporal dependencies and seasonality inherent in time-series data. Linear regression treats observations as independent, which isn't appropriate for sequential time-series data where patterns across time points are crucial.
Option C is INCORRECT. KMEANS is for clustering similar data points and has no forecasting capabilities. It groups similar observations together but cannot predict future values, making it inappropriate for revenue forecasting.
Option D is INCORRECT. AUTOML_CLASSIFIER is for classification problems, not for numerical predictions over time. It assigns observations to categories rather than forecasting continuous values like revenue, and it doesn't account for the temporal nature of the data.
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
