Google Professional Machine Learning Engineer Question 81
Select 3Google Cloud PlatformYou are a Machine Learning Engineer at a retail company that wants to predict future sales for its products based on historical sales data. You decide to use AutoML Tables to create a forecasting model. Which of the following steps are necessary to successfully build and deploy the forecasting model using AutoML Tables?
- A
Prepare the dataset by ensuring it includes a time column and correctly formatted target variable.
- B
Split the dataset into training, validation, and test datasets manually before uploading to AutoML Tables.
- C
Enable the 'Forecasting' objective when creating the AutoML Tables model.
- D
Set the forecast horizon and granularity of the time series data during model configuration.
- E
Manually tune model hyperparameters such as learning rate and number of layers after training.
Show answer and explanation
Correct answers: A, C, D
Explanation
To create a forecasting model with AutoML Tables, you need a properly prepared dataset that includes a time column and target variable. AutoML Tables provides an option to specify a forecasting objective, and you must configure details like the forecast horizon and granularity. Dataset splitting and hyperparameter tuning are handled automatically by AutoML Tables, so these steps do not need to be performed manually.
- A. Correct.
Correct: Preparing the dataset with a time column and target variable is a critical step for forecasting tasks in AutoML Tables.
- B. Incorrect.
Incorrect: AutoML Tables automatically splits the dataset into training, validation, and test sets during the model creation process, so this step is not required manually.
- C. Correct.
Correct: The 'Forecasting' objective must be selected to ensure that AutoML Tables builds a time series forecasting model.
- D. Correct.
Correct: Defining the forecast horizon and granularity helps AutoML Tables understand the time intervals and how far into the future predictions should be made.
- E. Incorrect.
Incorrect: AutoML Tables automatically handles hyperparameter tuning, so manual tuning is not required.