Google Professional Machine Learning Engineer Google Professional Machine Learning Engineer Online Training

Question #94

You are profiling the performance of your TensorFlow model training time and notice a performance issue caused by inefficiencies in the input data pipeline for a single 5 terabyte CSV file dataset on Cloud Storage. You need to optimize the input pipeline performance.

Which action should you try first to increase the efficiency of your pipeline?

A . Preprocess the input CSV file into a TFRecord file.
B . Randomly select a 10 gigabyte subset of the data to train your model.
C . Split into multiple CSV files and use a parallel interleave transformation.
D . Set the reshuffle_each_iteration parameter to true in the tf.data.Dataset.shuffle method.

Reveal Solution Hide Solution

Question #94

You are profiling the performance of your TensorFlow model training time and notice a performance issue caused by inefficiencies in the input data pipeline for a single 5 terabyte CSV file dataset on Cloud Storage. You need to optimize the input pipeline performance.

Which action should you try first to increase the efficiency of your pipeline?

A . Preprocess the input CSV file into a TFRecord file.
B . Randomly select a 10 gigabyte subset of the data to train your model.
C . Split into multiple CSV files and use a parallel interleave transformation.
D . Set the reshuffle_each_iteration parameter to true in the tf.data.Dataset.shuffle method.

Reveal Solution Hide Solution

Question #103

Export the batch prediction job outputs from Cloud Storage and import them into BigQuery.

Reveal Solution Hide Solution

Question #104

Your company manages an application that aggregates news articles from many different online sources and sends them to users. You need to build a recommendation model that will suggest articles to readers that are similar to the articles they are currently reading.

Which approach should you use?

A . Create a collaborative filtering system that recommends articles to a user based on the user’s past behavior.
B . Encode all articles into vectors using word2vec, and build a model that returns articles based on vector similarity.
C . Build a logistic regression model for each user that predicts whether an article should be recommended to a user.
D . Manually label a few hundred articles, and then train an SVM classifier based on the manually classified articles that categorizes additional articles into their respective categories.

Reveal Solution Hide Solution

Correct Answer: B
B

Explanation:

Option A is incorrect because creating a collaborative filtering system that recommends articles to a user based on the user’s past behavior is not the best approach to suggest articles that are similar to the articles they are currently reading. Collaborative filtering is a method of recommendation that uses the ratings or preferences of other users to predict the preferences of a target user1. However, this method does not consider the content or features of the articles, and may not be able to find articles that are similar in terms of topic, style, or sentiment.

Option B is correct because encoding all articles into vectors using word2vec, and building a model that returns articles based on vector similarity is a suitable approach to suggest articles that are similar to the articles they are currently reading. Word2vec is a technique that learns low-dimensional and dense representations of words from a large corpus of text, such that words that are semantically similar have similar vectors2. By applying word2vec to the articles, we can obtain vector representations of the articles that capture their meaning and usage. Then, we can use a similarity measure, such as cosine similarity, to find articles that have similar vectors to the current article3.

Option C is incorrect because building a logistic regression model for each user that predicts whether an article should be recommended to a user is not a feasible approach to suggest articles that are similar to the articles they are currently reading. Logistic regression is a supervised learning method that models the probability of a binary outcome (such as recommend or not) based on some input features (such as user profile or article content)4. However, this method requires a large amount of labeled data for each user, which may not be available or scalable. Moreover, this method does not directly measure the similarity between articles, but rather the likelihood of a user’s preference.

Option D is incorrect because manually labeling a few hundred articles, and then training an SVM classifier based on the manually classified articles that categorizes additional articles into their respective categories is not an effective approach to suggest articles that are similar to the articles they are currently reading. SVM (support vector machine) is a supervised learning method that finds a hyperplane that separates the data into different classes (such as news categories) with the maximum margin5. However, this method also requires a large amount of labeled data, which may be costly and time-consuming to obtain. Moreover, this method does not account for the fine-grained similarity between articles within the same category, or the cross-category similarity between articles from different categories.

Reference: Collaborative filtering

Word2vec

Cosine similarity

Logistic regression

SVM

Question #105

You work for a large social network service provider whose users post articles and discuss news. Millions of comments are posted online each day, and more than 200 human moderators constantly review comments and flag those that are inappropriate. Your team is building an ML model to help human moderators check content on the platform. The model scores each comment and flags suspicious comments to be reviewed by a human.

Which metric(s) should you use to monitor the model’s performance?

A . Number of messages flagged by the model per minute
B . Number of messages flagged by the model per minute confirmed as being inappropriate by humans.
C . Precision and recall estimates based on a random sample of 0.1% of raw messages each minute sent to a human for review
D . Precision and recall estimates based on a sample of messages flagged by the model as potentially inappropriate each minute

Reveal Solution Hide Solution

Question #106

You have been given a dataset with sales predictions based on your company’s marketing activities. The data is structured and stored in BigQuery, and has been carefully managed by a team of data analysts. You need to prepare a report providing insights into the predictive capabilities of the data. You were asked to run several ML models with different levels of sophistication, including simple models and multilayered neural networks. You only have a few hours to gather the results of your experiments.

Which Google Cloud tools should you use to complete this task in the most efficient and self-serviced way?

A . Use BigQuery ML to run several regression models, and analyze their performance.
B . Read the data from BigQuery using Dataproc, and run several models using SparkML.
C . Use Vertex AI Workbench user-managed notebooks with scikit-learn code for a variety of ML algorithms and performance metrics.
D . Train a custom TensorFlow model with Vertex AI, reading the data from BigQuery featuring a variety of ML algorithms.

Reveal Solution Hide Solution

Correct Answer: A
A

Explanation:

Option A is correct because using BigQuery ML to run several regression models, and analyze their performance is the most efficient and self-serviced way to complete the task. BigQuery ML is a service that allows you to create and use ML models within BigQuery using SQL queries1. You can use BigQuery ML to run different types of regression models, such as linear regression, logistic regression, or DNN regression2. You can also use BigQuery ML to analyze the performance of your models, such as the mean squared error, the accuracy, or the ROC curve3. BigQuery ML is fast, scalable, and easy to use, as it does not require any data movement, coding, or additional tools4.

Option B is incorrect because reading the data from BigQuery using Dataproc, and running several models using SparkML is not the most efficient and self-serviced way to complete the task. Dataproc is a service that allows you to create and manage clusters of virtual machines that run Apache Spark and other open-source tools5. SparkML is a library that provides ML algorithms and utilities for Spark. However, this option requires more effort and resources than option A, as it involves moving the data from BigQuery to Dataproc, creating and configuring the clusters, writing and running the SparkML code, and analyzing the results.

Option C is incorrect because using Vertex AI Workbench user-managed notebooks with scikit-learn code for a variety of ML algorithms and performance metrics is not the most efficient and self-serviced way to complete the task. Vertex AI Workbench is a service that allows you to create and use notebooks for ML development and experimentation. Scikit-learn is a library that provides ML algorithms and utilities for Python. However, this option also requires more effort and resources than option A, as it involves creating and managing the notebooks, writing and running the scikit-learn code, and analyzing the results.

Option D is incorrect because training a custom TensorFlow model with Vertex AI, reading the data from BigQuery featuring a variety of ML algorithms is not the most efficient and self-serviced way to complete the task. TensorFlow is a framework that allows you to create and train ML models using Python or other languages. Vertex AI is a service that allows you to train and deploy ML models using built-in algorithms or custom containers. However, this option also requires more effort and resources than option A, as it involves writing and running the TensorFlow code, creating and managing the training jobs, and analyzing the results.

Reference: BigQuery ML overview

Creating a model in BigQuery ML

Evaluating a model in BigQuery ML

BigQuery ML benefits

Dataproc overview

[SparkML overview]

[Vertex AI Workbench overview]

[Scikit-learn overview]

[TensorFlow overview]

[Vertex AI overview]

Question #107

You are an ML engineer at a bank. You have developed a binary classification model using AutoML Tables to predict whether a customer will make loan payments on time. The output is used to approve or reject loan requests. One customer’s loan request has been rejected by your model, and the bank’s risks department is asking you to provide the reasons that contributed to the model’s decision.

What should you do?

A . Use local feature importance from the predictions.
B . Use the correlation with target values in the data summary page.
C . Use the feature importance percentages in the model evaluation page.
D . Vary features independently to identify the threshold per feature that changes the classification.

Reveal Solution Hide Solution

Correct Answer: A
A

Explanation:

Option A is correct because using local feature importance from the predictions is the best way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. Local feature importance is a measure of how much each feature affects the prediction for a given instance, relative to the average prediction for the dataset1. AutoML Tables provides local feature importance values for each prediction, which can be accessed using the Vertex AI SDK for Python or the Cloud Console2. By using local feature importance, you can explain why the model rejected the loan request based on the customer’s data.

Option B is incorrect because using the correlation with target values in the data summary page is not a good way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. The correlation with target values is a measure of how much each feature is linearly related to the target variable for the entire dataset, not for a single instance3. The data summary page in AutoML Tables shows the correlation with target values for each feature, as well as other statistics such as mean, standard deviation, and histogram4. However, these statistics are not useful for explaining the model’s decision for a specific customer, as they do not account for the interactions between features or the non-linearity of the model.

Option C is incorrect because using the feature importance percentages in the model evaluation page is not a good way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. The feature importance percentages are a measure of how much each feature affects the overall accuracy of the model for the entire dataset, not for a single instance5. The model evaluation page in AutoML Tables shows the feature importance percentages for each feature, as well as other metrics such as precision, recall, and confusion matrix. However, these metrics are not useful for explaining the model’s decision for a specific customer, as they do not reflect the individual contribution of each feature for a given prediction.

Option D is incorrect because varying features independently to identify the threshold per feature that changes the classification is not a feasible way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. This method involves changing the value of one feature at a time, while keeping the other features constant, and observing how the prediction changes. However, this method is not practical, as it requires making multiple prediction requests, and may not capture the interactions between features or the non-linearity of the model.

Reference: Local feature importance

Getting local feature importance values

Correlation with target values

Data summary page

Feature importance percentages

[Model evaluation page]

[Varying features independently]

Question #108

You work for a magazine distributor and need to build a model that predicts which customers will renew their subscriptions for the upcoming year. Using your company’s historical data as your training set, you created a TensorFlow model and deployed it to AI Platform. You need to determine which customer attribute has the most predictive power for each prediction served by the model.

What should you do?

A . Use AI Platform notebooks to perform a Lasso regression analysis on your model, which will eliminate features that do not provide a strong signal.
B . Stream prediction results to BigQuery. Use BigQuery’s CORR (X1, X2) function to calculate the Pearson correlation coefficient between each feature and the target variable.
C . Use the AI Explanations feature on AI Platform. Submit each prediction request with the ‘explain’ keyword to retrieve feature attributions using the sampled Shapley method.
D . Use the What-If tool in Google Cloud to determine how your model will perform when individual features are excluded. Rank the feature importance in order of those that caused the most significant performance drop when removed from the model.

Reveal Solution Hide Solution

Correct Answer: C
C

Explanation:

Option A is incorrect because using AI Platform notebooks to perform a Lasso regression analysis on your model, which will eliminate features that do not provide a strong signal, is not a suitable way to determine which customer attribute has the most predictive power for each prediction served by the model. Lasso regression is a method of feature selection that applies a penalty to the coefficients of the linear model, and shrinks them to zero for irrelevant features1. However, this method assumes that the model is linear and additive, which may not be the case for a TensorFlow model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.

Option B is incorrect because streaming prediction results to BigQuery, and using BigQuery’s CORR(X1, X2) function to calculate the Pearson correlation coefficient between each feature and the target variable, is not a valid way to determine which customer attribute has the most predictive power for each prediction served by the model. The Pearson correlation coefficient is a measure of the linear relationship between two variables, ranging from -1 to 12. However, this method does not account for the interactions between features or the non-linearity of the model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.

Option C is correct because using the AI Explanations feature on AI Platform, and submitting each prediction request with the ‘explain’ keyword to retrieve feature attributions using the sampled Shapley method, is the best way to determine which customer attribute has the most predictive power for each prediction served by the model. AI Explanations is a service that allows you to get feature attributions for your deployed models on AI Platform3. Feature attributions are values that indicate how much each feature contributed to the prediction for a given instance4. The sampled Shapley method is a technique that uses the Shapley value, a game-theoretic concept, to measure the contribution of each feature to the prediction5. By using AI Explanations, you can get feature attributions for each prediction request, and identify the most important features for each customer.

Option D is incorrect because using the What-If tool in Google Cloud to determine how your model will perform when individual features are excluded, and ranking the feature importance in order of those that caused the most significant performance drop when removed from the model, is not a practical way to determine which customer attribute has the most predictive power for each prediction served by the model. The What-If tool is a tool that allows you to visualize and analyze your ML models and datasets. However, this method requires manually editing or removing features for each instance, and observing the change in the prediction. This method is not scalable or efficient, and may not capture the interactions between features or the non-linearity of the model.

Reference: Lasso regression

Pearson correlation coefficient

AI Explanations overview

Feature attributions

Sampled Shapley method

[What-If tool overview]

Question #109

You are working on a binary classification ML algorithm that detects whether an image of a classified scanned document contains a company’s logo. In the dataset, 96% of examples don’t have the logo, so the dataset is very skewed.

Which metrics would give you the most confidence in your model?

A . F-score where recall is weighed more than precision
B . RMSE
C . F1 score
D . F-score where precision is weighed more than recall

Reveal Solution Hide Solution

Correct Answer: A
A

Explanation:

Option A is correct because using F-score where recall is weighed more than precision is a suitable metric for binary classification with imbalanced data. F-score is a harmonic mean of precision and recall, which are two metrics that measure the accuracy and completeness of the positive class1. Precision is the fraction of true positives among all predicted positives, while recall is the fraction of true positives among all actual positives1. When the data is imbalanced, the positive class is the minority class, which is usually the class of interest. For example, in this case, the positive class is the images that contain the company’s logo, which are rare but important to detect. By weighing recall more than precision, we can emphasize the importance of finding all the positive examples, even if some false positives are included2.

Option B is incorrect because using RMSE (root mean squared error) is not a valid metric for binary classification with imbalanced data. RMSE is a metric that measures the average magnitude of the errors between the predicted and actual values3. RMSE is suitable for regression problems, where the target variable is continuous, not for classification problems, where the target variable is discrete4.

Option C is incorrect because using F1 score is not the best metric for binary classification with imbalanced data. F1 score is a special case of F-score where precision and recall are equally weighted1. F1 score is suitable for balanced data, where the positive and negative classes are equally important and frequent5. However, for imbalanced data, the positive class is more important and less frequent than the negative class, so F1 score may not reflect the performance of the model well2.

Option D is incorrect because using F-score where precision is weighed more than recall is not a good metric for binary classification with imbalanced data. By weighing precision more than recall, we can emphasize the importance of minimizing the false positives, even if some true positives are missed2. However, for imbalanced data, the true positives are more important and less frequent than the false positives, so this metric may not reflect the performance of the model well2.

Reference: Precision, recall, and F-measure

F-score for imbalanced data

RMSE

Regression vs classification

F1 score

[Imbalanced classification]

[Binary classification]

Question #110

You work on the data science team for a multinational beverage company. You need to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. You are provided with historical data that includes product types, product sales volumes, expenses, and profits for all regions.

What should you use as the input and output for your model?

A . Use latitude, longitude, and product type as features. Use profit as model output.
B . Use latitude, longitude, and product type as features. Use revenue and expenses as model outputs.
C . Use product type and the feature cross of latitude with longitude, followed by binning, as features.
Use profit as model output.
D . Use product type and the feature cross of latitude with longitude, followed by binning, as features. Use revenue and expenses as model outputs.

Reveal Solution Hide Solution

Correct Answer: C
C

Explanation:

Option A is incorrect because using latitude, longitude, and product type as features, and using profit as model output is not the best way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option does not capture the interaction between latitude and longitude, which may affect the profitability of the product. For example, the same product may have different profitability in different regions, depending on the climate, culture, or preferences of the customers. Moreover, this option does not account for the granularity of the location data, which may be too fine or too coarse for the model. For example, using the exact coordinates of a city may not be meaningful, as the profitability may vary within the city, or using the country name may not be informative, as the profitability may vary across the country.

Option B is incorrect because using latitude, longitude, and product type as features, and using revenue and expenses as model outputs is not a suitable way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option has the same drawbacks as option A, as it does not capture the interaction between latitude and longitude, or account for the granularity of the location data. Moreover, this option does not directly predict the profitability of the product, which is the target variable of interest. Instead, it predicts the revenue and expenses of the product, which are intermediate variables that depend on other factors, such as the price, the cost, or the demand of the product. To obtain the profitability, we would need to subtract the expenses from the revenue, which may introduce errors or uncertainties in the prediction.

Option C is correct because using product type and the feature cross of latitude with longitude, followed by binning, as features, and using profit as model output is a good way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option captures the interaction between latitude and longitude, which may affect the profitability of the product, by creating a feature cross of these two features. A feature cross is a synthetic feature that combines the values of two or more features into a single feature1. This option also accounts for the granularity of the location data, by binning the feature cross into discrete buckets. Binning is a technique that groups continuous values into intervals, which can reduce the noise and complexity of the data2. Moreover, this option directly predicts the profitability of the product, which is the target variable of interest, by using it as the model output.

Option D is incorrect because using product type and the feature cross of latitude with longitude, followed by binning, as features, and using revenue and expenses as model outputs is not a valid way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option has the same advantages as option C, as it captures the interaction between latitude and longitude, and accounts for the granularity of the location data, by creating a feature cross and binning it. However, this option does not directly predict the profitability of the product, which is the target variable of interest, but rather predicts the revenue and expenses of the product, which are intermediate variables that depend on other factors, as explained in option B.

Reference: Feature cross

Binning

[Profitability]

[Revenue and expenses]

[Latitude and longitude]

[Product type]