Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
You work for a hospital that wants to optimize how it schedules operations to ensure that bed usage is efficiently managed. To achieve this, you need to create a machine learning model that can predict the number of beds needed for patients each day based on the number of scheduled surgeries. The hospital has provided one year of historical data, organized in 365 rows, with the following variables for each day:
• Number of scheduled surgeries
• Number of beds occupied
• Date (to capture temporal patterns)
Given the requirement to maximize the speed of model development and testing, which method should you choose to build this predictive model?
You work for a hospital that wants to optimize how it schedules operations to ensure that bed usage is efficiently managed. To achieve this, you need to create a machine learning model that can predict the number of beds needed for patients each day based on the number of scheduled surgeries. The hospital has provided one year of historical data, organized in 365 rows, with the following variables for each day: • Number of scheduled surgeries • Number of beds occupied • Date (to capture temporal patterns) Given the requirement to maximize the speed of model development and testing, which method should you choose to build this predictive model?
Explanation:
Option D is the best choice because Vertex AI AutoML Forecasting is designed for time series forecasting, which is well-suited for predicting the number of beds needed each day. By using 'date' as the time variable and 'number of scheduled surgeries' as a covariate, the model can account for temporal patterns and the direct influence of surgeries on bed occupancy. This approach automates much of the modeling process, including feature selection and hyperparameter tuning, which speeds up model development and ensures that both the time series aspect and the predictive variable are incorporated effectively.