Question 1

You are planning an ML project to predict housing prices based on various features (e.g., square footage, location, number of bedrooms). Which of the following is the best approach to ensure a successful ML project outcome in terms of planning the data collection, model training, and evaluation?

Options :

A : Begin with data collection, then train several models, and finally decide on the project’s objectives based on initial results.

B : Train a simple model first without defining evaluation metrics, as this allows for flexibility in metrics later.

C : Start by selecting a complex deep learning model to ensure high accuracy, then collect data to match the model’s requirements.

D : First, define the project’s objectives, then determine data collection methods to gather relevant and high-quality data.

Answer: D

Question 2

Your team needs to automate a data processing workflow where a new file upload in a Cloud Storage bucket triggers an ETL process. This ETL process is managed by a Dataflow job, which should start only when a new file is uploaded. Which combination of Google Cloud services should you use to set up this event-driven pipeline?

Options :

A : Cloud Composer and Cloud Functions

B : Eventarc and Cloud Run

C : Dataform and BigQuery

D : Eventarc and Dataflow

Answer: D

Question 3

Which of the following metrics is most appropriate for evaluating a binary classification model when the dataset has an imbalanced distribution of classes?

Options :

A : Precision

B : Accuracy

C : F1 Score

D : Recall

Answer: C

Question 4

You manage an ecommerce website that has a diverse range of products. You need to forecast future product demand accurately to ensure that your company has sufficient inventory to meet customer needs and avoid stockouts. Your company's historical sales data is stored in a BigQuery table. You need to create a scalable solution that takes into account the seasonality and historical data to predict product demand. What should you do?

Options :

A : Use the historical sales data to train and create a BigQuery ML time series model. Use the ML.FORECAST function call to output the predictions into a new BigQuery table.

B : Use Colab Enterprise to create a Jupyter notebook. Use the historical sales data to train a custom prediction model in Python.

C : Use the historical sales data to train and create a BigQuery ML linear regression model. Use the ML.PREDICT function call to output the predictions into a new BigQuery table.

D : Use the historical sales data to train and create a BigQuery ML logistic regression model. Use the ML.PREDICT function call to output the predictions into a new BigQuery table.

Answer: A

Question 5

You are a data analyst tasked with visualizing sales data for a large retail company. The company needs a dashboard that provides real-time insights into sales trends across different regions and product categories. Given the requirement for scalable data visualization, collaboration across multiple teams, and the ability to create custom, SQL-based metrics, which tool would best suit the company's needs?

Options :

A : Tableau

B : Google Sheets

C : Looker

D : Google Data Studio

Answer: C

Free Associate-Data-Practitioner Mock Exam – Practice Online Confidently

Buying Options: