Google Professional Machine Learning Engineer Exam - Topic 8 Question 65 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam

Question #: 65
Topic #: 8

[All Professional Machine Learning Engineer Questions]

You work for a hospital that wants to optimize how it schedules operations. You need to create a model that uses the relationship between the number of surgeries scheduled and beds used You want to predict how many beds will be needed for patients each day in advance based on the scheduled surgeries You have one year of data for the hospital organized in 365 rows

The data includes the following variables for each day

* Number of scheduled surgeries

* Number of beds occupied

* Date

You want to maximize the speed of model development and testing What should you do?

ACreate a BigQuery table Use BigQuery ML to build a regression model, with number of beds as the target variable and number of scheduled surgeries and date features (such as day of week) as the predictors

BCreate a BigQuery table Use BigQuery ML to build an ARIMA model, with number of beds as the target variable and date as the time variable.

CCreate a Vertex Al tabular dataset Tram an AutoML regression model, with number of beds as the target variable and number of scheduled minor surgeries and date features (such as day of the week) as the predictors

DCreate a Vertex Al tabular dataset Train a Vertex Al AutoML Forecasting model with number of beds as the target variable, number of scheduled surgeries as a covariate, and date as the time variable.

Show Suggested Answer

Suggested Answer: D

This approach would allow you to keep the critical columns of data while reducing the sensitivity of the dataset by removing the personally identifiable information (PII) before training the model. By creating an authorized view of the data, you can ensure that sensitive values cannot be accessed by unauthorized individuals.

by Adell at Oct 08, 2023, 06:02 PM

Limited Time Offer

25%

Off

Get Premium Professional Machine Learning Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Tran

3 months ago

Wait, can we really predict beds just from surgeries? Seems off.

upvoted 0 times

...

Laticia

3 months ago

Totally agree with A, regression models are fast!

upvoted 0 times

...

Ceola

4 months ago

C sounds interesting, but not sure about the minor surgeries part.

upvoted 0 times

...

Cammy

4 months ago

I think D might be better for forecasting.

upvoted 0 times

...

Alida

4 months ago

A is the way to go for quick results!

upvoted 0 times

...

Dominque

4 months ago

I feel like option D might be the best choice since it combines forecasting with the surgeries as a covariate, but I need to double-check how that impacts the predictions.

upvoted 0 times

...

Mabel

4 months ago

I practiced with AutoML before, and I think option C could work well since it allows for quick model training, but I'm unsure about the specifics of the features.

upvoted 0 times

...

Lynda

4 months ago

I'm not entirely sure, but I think ARIMA models are more suited for time series data, which makes option B a bit tempting, though it might not consider the surgeries directly.

upvoted 0 times

...

Josue

5 months ago

I remember we discussed using regression models for predicting continuous variables like bed occupancy, so option A seems like a good fit.

upvoted 0 times

...

Mitzie

5 months ago

I'm feeling pretty confident about this one. I think Option A is the way to go - it's the most straightforward approach and should get us a working model quickly. The date features will help capture any seasonal patterns in the data.

upvoted 0 times

...

Cecilia

5 months ago

Hmm, I'm a bit confused by the time series aspect of this. Should we be using an ARIMA model instead? Option B seems like it might be a better fit since we have the date information.

upvoted 0 times

...

Colene

5 months ago

This looks like a classic regression problem to predict the number of beds needed based on the number of scheduled surgeries. I think Option A using BigQuery ML would be the fastest approach to get a working model.

upvoted 0 times

...

Catrice

5 months ago

I'm not as familiar with BigQuery ML, but the AutoML options in Option C and D sound interesting. The Vertex AI Forecasting model in Option D could be a good way to handle the time series element.

upvoted 0 times

...

Mariko

5 months ago

Hmm, I'm a bit unsure about the aggregation and next-hop-self commands. I'll need to double-check the BGP best practices to make sure I understand how those work.

upvoted 0 times

...

Brandon

5 months ago

This feels similar to a question we answered about network configurations. I want to say it's 30 shelves, but I could be mixing it up.

upvoted 0 times

...

Sue

5 months ago

Hmm, I'm a little unsure about this one. I'll have to think through the different chart types and how they're used.

upvoted 0 times

...

Marvel

5 months ago

This seems like a straightforward question about the purpose of security portfolio assessments. I'll need to carefully consider each option and think about the key objectives of these assessments.

upvoted 0 times

...

Mirta

5 months ago

I remember similar questions on baseline conditions, and I think options like "stable" can sometimes be tricky.

upvoted 0 times

...

Laurel

10 months ago

Yeah, no need to overcomplicate things. BigQuery ML is the clear winner here. Get those bed predictions cranking in no time!

upvoted 0 times

Ludivina

9 months ago

D) Create a Vertex AI tabular dataset Train a Vertex AI AutoML Forecasting model with number of beds as the target variable, number of scheduled surgeries as a covariate, and date as the time variable.

upvoted 0 times

...

Hana

10 months ago

Yeah, BigQuery ML is definitely the way to go for quick and accurate predictions.

upvoted 0 times

...

Emogene

10 months ago

A) Create a BigQuery table Use BigQuery ML to build a regression model, with number of beds as the target variable and number of scheduled surgeries and date features (such as day of week) as the predictors

upvoted 0 times

...

Hailey

10 months ago

Ha! Vertex AI, really? That's overkill for this simple use case. BigQuery ML is perfect - fast and easy.

upvoted 0 times

Solange

9 months ago

B) Create a BigQuery table Use BigQuery ML to build an ARIMA model, with number of beds as the target variable and date as the time variable.

upvoted 0 times

...

Erasmo

9 months ago

Ha! Vertex AI, really? That's overkill for this simple use case. BigQuery ML is perfect - fast and easy.

upvoted 0 times

...

Shay

10 months ago

upvoted 0 times

...

Sherrell

10 months ago

I agree, using BigQuery ML is the easiest approach. I like how it handles the data prep and model training for us.

upvoted 0 times

Jess

10 months ago

I agree, using BigQuery ML is the easiest approach. I like how it handles the data prep and model training for us.

upvoted 0 times

...

Lavera

10 months ago

upvoted 0 times

...

Matilda

11 months ago

BigQuery ML seems like the way to go here. I can quickly build a regression model and get predictions without having to worry about the infrastructure.

upvoted 0 times