Google Professional Machine Learning Engineer Practice Test - Questions Answers, Page 8

AutoML Tables is a service that allows you to automatically build, analyze, and deploy machine learning models on tabular data. It is suitable for large-scale regression and classification problems, and it supports various optimization objectives, data splitting methods, and hyperparameter tuning algorithms. AutoML Tables can handle both categorical and numerical features, and it can also handle missing values and outliers. AutoML Tables is a good choice for this problem because it minimizes the effort and training time required to train a regression model, while maximizing the model performance.

RMSLE stands for Root Mean Squared Logarithmic Error, and it is a metric that measures the average difference between the logarithm of the predicted values and the logarithm of the actual values. RMSLE is useful for regression problems where the target variable can include negative values, and where large differences between small values are more important than large differences between large values. For example, RMSLE penalizes underestimating a value of 10 by 2 more than overestimating a value of 1000 by 20. RMSLE is a good optimization objective for this problem because it can handle negative values in the target variable, and it can reduce the impact of outliers and large errors.

For more information about AutoML Tables and RMSLE, see the following references:

AutoML Tables: end-to-end workflows on AI Platform Pipelines

Predict workload failures before they happen with AutoML Tables

How to Calculate RMSE in R

The most likely problem is that the tables that you created to hold your training and validation records share some records, and you may not be using all the data in your initial table. This is because the RAND() function generates a random number between 0 and 1 for each row, and the probability of a row being in both the training and validation tables is 0.2 * 0.8 = 0.16, which is not negligible. This means that some of the records that you use to validate your model are also used to train your model, which can lead to overfitting and poor generalization. Moreover, the probability of a row being in neither the training nor the validation table is 0.2 * 0.2 = 0.04, which means that you are wasting some of the data in your initial table and reducing the size of your datasets. A better way to split your data into training and validation sets is to use a hash function on a unique identifier column, such as the following queries:

CREATE OR REPLACE TABLE 'myproject.mydataset.training' AS (SELECT * FROM 'myproject.mydataset.mytable' WHERE MOD(FARM_FINGERPRINT(id), 10) < 8); CREATE OR REPLACE TABLE 'myproject.mydataset.validation' AS (SELECT * FROM 'myproject.mydataset.mytable' WHERE MOD(FARM_FINGERPRINT(id), 10) >= 8);

This way, you can ensure that each row has a fixed 80% chance of being in the training table and a 20% chance of being in the validation table, without any overlap or omission.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

BigQuery ML: Splitting data for training and testing

BigQuery: FARM_FINGERPRINT function

The best option to ensure real-time ingestion of the user activity data into BigQuery is to run a Dataflow streaming job to ingest the data into BigQuery. Dataflow is a fully managed service that can handle both batch and stream processing of data, and can integrate seamlessly with BigQuery and other Google Cloud services. Dataflow can also use Apache Beam as the programming model, which provides a unified and portable API for developing data pipelines. By using Dataflow, you can avoid the complexity and overhead of managing your own infrastructure, and focus on the logic and transformation of your data. Dataflow can also handle various types of data, such as structured, unstructured, or binary data, and can apply windowing, aggregation, and other operations on the data streams.

The other options are not optimal for the following reasons:

A) Configuring Pub/Sub to stream the data into BigQuery is not a good option, as Pub/Sub is a messaging service that can publish and subscribe to data streams, but cannot perform any transformation or processing on the data. Pub/Sub can be used as a source or a sink for Dataflow, but not as a standalone solution for ingesting data into BigQuery.

B) Running an Apache Spark streaming job on Dataproc to ingest the data into BigQuery is not a good option, as it requires setting up and managing your own cluster of virtual machines, which can increase the cost and complexity of your solution. Moreover, Apache Spark is not natively integrated with BigQuery, and requires using connectors or intermediate storage to write data to BigQuery, which can introduce latency and inefficiency.

D) Configuring Pub/Sub and a Dataflow streaming job to ingest the data into BigQuery is not a bad option, but it is not necessary, as Dataflow can directly read data from the mobile applications without using Pub/Sub as an intermediary. Using Pub/Sub can add an extra layer of abstraction and reliability, but it can also increase the cost and complexity of your solution, and introduce some delay in the data ingestion.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Dataflow documentation

BigQuery documentation

The best business metric to track to measure the model's performance is user engagement as measured by the number of battles played daily per user. This metric reflects the main goal of the model, which is to enhance the user experience and satisfaction by creating balanced and fair battles. If the model is successful, it should increase the user retention and loyalty, as well as the word-of-mouth and referrals. This metric is also easy to measure and interpret, as it can be directly obtained from the user activity data.

The other options are not optimal for the following reasons:

A) Average time players wait before being assigned to a team is not a good metric, as it does not capture the quality or outcome of the battles. It only measures the efficiency of the model, which is not the primary objective. Moreover, this metric can be influenced by external factors, such as the availability and demand of players, the network latency, and the server capacity.

B) Precision and recall of assigning players to teams based on their predicted versus actual ability is not a good metric, as it is difficult to measure and interpret. It requires having a reliable and consistent way of estimating the player's ability, which can be subjective and dynamic. It also requires having a ground truth label for each assignment, which can be costly and impractical to obtain. Moreover, this metric does not reflect the user feedback or satisfaction, which is the ultimate goal of the model.

D) Rate of return as measured by additional revenue generated minus the cost of developing a new model is not a good metric, as it is not directly related to the model's performance. It measures the profitability of the model, which is a secondary objective. Moreover, this metric can be affected by many other factors, such as the market conditions, the pricing strategy, the marketing campaigns, and the competition.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

How to measure user engagement

How to choose the right metrics for your machine learning model

The best option to ensure that the features with the largest magnitude don't overfit the model is to normalize the data by scaling it to have values between 0 and 1. This is also known as min-max scaling or feature scaling, and it can reduce the variance and skewness of the data, as well as improve the numerical stability and convergence of the model. Normalizing the data can also make the model less sensitive to the scale of the features, and more focused on the relative importance of each feature. Normalizing the data can be done using various methods, such as dividing each value by the maximum value, subtracting the minimum value and dividing by the range, or using the sklearn.preprocessing.MinMaxScaler function in Python.

The other options are not optimal for the following reasons:

A) Standardizing the data by transforming it with a logarithmic function is not a good option, as it can distort the distribution and relationship of the data, and introduce bias and errors. Moreover, the logarithmic function is not defined for negative or zero values, which can limit its applicability and cause problems for the model.

B) Applying a principal component analysis (PCA) to minimize the effect of any particular feature is not a good option, as it can reduce the interpretability and explainability of the data and the model. PCA is a dimensionality reduction technique that transforms the data into a new set of orthogonal features that capture the most variance in the data. However, these new features are not directly related to the original features, and can lose some information and meaning in the process. Moreover, PCA can be computationally expensive and complex, and may not be necessary for the problem at hand.

C) Using a binning strategy to replace the magnitude of each feature with the appropriate bin number is not a good option, as it can lose the granularity and precision of the data, and introduce noise and outliers. Binning is a discretization technique that groups the continuous values of a feature into a finite number of bins or categories. However, this can reduce the variability and diversity of the data, and create artificial boundaries and gaps that may not reflect the true nature of the data. Moreover, binning can be arbitrary and subjective, and depend on the choice of the bin size and number.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Feature Scaling for Machine Learning: Understanding the Difference Between Normalization vs. Standardization sklearn.preprocessing.MinMaxScaler documentation

Principal Component Analysis Explained Visually

Binning Data in Python

The best hardware to choose for your models is a cluster with 2 a2-megagpu-16g machines, each with 16 NVIDIA Tesla A100 GPUs (640 GB GPU memory in total), 96 vCPUs, and 1.4 TB RAM. This hardware configuration can provide you with enough compute power, memory, and bandwidth to handle your large and complex deep learning models, as well as your custom TensorFlow ops in C++. The NVIDIA Tesla A100 GPUs are the latest and most advanced GPUs from NVIDIA, which offer high performance, scalability, and efficiency for various ML workloads. They also support multi-instance GPU (MIG) technology, which allows you to partition each GPU into up to seven smaller instances, each with its own memory, cache, and compute cores. This can enable you to run multiple experiments in parallel, or to optimize the resource utilization and cost efficiency of your models. The a2-megagpu-16g machines are part of the Google Cloud Accelerator-Optimized VM (A2) family, which are designed to provide the best performance and flexibility for GPU-intensive applications. They also offer high-speed NVLink interconnects between the GPUs, which can improve the data transfer and communication between the GPUs. Moreover, the a2-megagpu-16g machines have 96 vCPUs and 1.4 TB RAM, which can support the CPU and memory requirements of your models, as well as the data preprocessing and postprocessing tasks.

The other options are not optimal for the following reasons:

A) A cluster with 2 n1-highcpu-64 machines, each with 8 NVIDIA Tesla V100 GPUs (128 GB GPU memory in total), and a n1-highcpu-64 machine with 64 vCPUs and 58 GB RAM is not a good option, as it has less GPU memory, compute power, and bandwidth than the a2-megagpu-16g machines. The NVIDIA Tesla V100 GPUs are the previous generation of GPUs from NVIDIA, which have lower performance, scalability, and efficiency than the NVIDIA Tesla A100 GPUs. They also do not support the MIG technology, which can limit the flexibility and optimization of your models. Moreover, the n1-highcpu-64 machines are part of the Google Cloud N1 VM family, which are general-purpose VMs that do not offer the best performance and features for GPU-intensive applications. They also have lower vCPUs and RAM than the a2-megagpu-16g machines, which can affect the CPU and memory requirements of your models, as well as the data preprocessing and postprocessing tasks.

C) A cluster with an n1-highcpu-64 machine with a v2-8 TPU and 64 GB RAM is not a good option, as it has less GPU memory, compute power, and bandwidth than the a2-megagpu-16g machines. The v2-8 TPU is a cloud tensor processing unit (TPU) device, which is a custom ASIC chip designed by Google to accelerate ML workloads. However, the v2-8 TPU is the second generation of TPUs, which have lower performance, scalability, and efficiency than the latest v3-8 TPUs. They also have less memory and bandwidth than the NVIDIA Tesla A100 GPUs, which can limit the size and complexity of your models, as well as the data transfer and communication between the devices. Moreover, the n1-highcpu-64 machine has lower vCPUs and RAM than the a2-megagpu-16g machines, which can affect the CPU and memory requirements of your models, as well as the data preprocessing and postprocessing tasks.

D) A cluster with 4 n1-highcpu-96 machines, each with 96 vCPUs and 86 GB RAM is not a good option, as it does not have any GPUs, which are essential for accelerating deep learning models. The n1-highcpu-96 machines are part of the Google Cloud N1 VM family, which are general-purpose VMs that do not offer the best performance and features for GPU-intensive applications. They also have lower RAM than the a2-megagpu-16g machines, which can affect the memory requirements of your models, as well as the data preprocessing and postprocessing tasks.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

NVIDIA Tesla A100 GPU

Google Cloud Accelerator-Optimized VM (A2) family

Google Cloud N1 VM family

Cloud TPU

The best approach to build a model that predicts how much inventory the logistics team should order each month is to use a time series forecasting model to predict each item's monthly sales. This approach can capture the temporal patterns and trends in the sales data, such as seasonality, cyclicality, and autocorrelation. It can also account for the variability and uncertainty in the demand, and provide confidence intervals and error metrics for the predictions. By using a time series forecasting model, you can provide the logistics team with accurate and reliable estimates of the future sales for each item, which can help them optimize the inventory levels and avoid overstocking or understocking. You can use various methods and tools to build a time series forecasting model, such as ARIMA, LSTM, Prophet, or BigQuery ML.

The other options are not optimal for the following reasons:

A) Using a clustering algorithm to group popular items together is not a good approach, as it does not provide any quantitative or temporal information about the sales or the inventory. It only provides a qualitative and static categorization of the items based on their similarity or dissimilarity. Moreover, clustering is an unsupervised learning technique, which does not use any target variable or feedback to guide the learning process. This can result in arbitrary and inconsistent clusters, which may not reflect the true demand or preferences of the customers.

B) Using a regression model to predict how much additional inventory should be purchased each month is not a good approach, as it does not account for the individual differences and dynamics of each item. It only provides a single aggregated value for the whole inventory, which can be misleading and inaccurate. Moreover, a regression model is not well-suited for handling time series data, as it assumes that the data points are independent and identically distributed, which is not the case for sales data. A regression model can also suffer from overfitting or underfitting, depending on the choice and complexity of the features and the model.

D) Using a classification model to classify inventory levels as UNDER_STOCKED, OVER_STOCKED, and CORRECTLY_STOCKED is not a good approach, as it does not provide any numerical or predictive information about the sales or the inventory. It only provides a discrete and subjective label for the inventory levels, which can be vague and ambiguous. Moreover, a classification model is not well-suited for handling time series data, as it assumes that the data points are independent and identically distributed, which is not the case for sales data. A classification model can also suffer from class imbalance, misclassification, or overfitting, depending on the choice and complexity of the features, the model, and the threshold.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Time Series Forecasting: Principles and Practice

BigQuery ML: Time series analysis

The best hardware to choose for your model while minimizing cost is a Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with a preemptible v3-8 TPU. This hardware configuration can provide you with high performance, scalability, and efficiency for your TensorFlow model, as well as low cost and flexibility for your long-running and checkpointing process. The v3-8 TPU is a cloud tensor processing unit (TPU) device, which is a custom ASIC chip designed by Google to accelerate ML workloads. It can handle large and complex models and datasets, and offer fast and stable training and inference. The n1-standard-16 is a general-purpose VM that can support the CPU and memory requirements of your model, as well as the data preprocessing and postprocessing tasks. By choosing a preemptible v3-8 TPU, you can take advantage of the lower price and availability of the TPU devices, as long as you can tolerate the possibility of the device being reclaimed by Google at any time. However, since you have built frequent checkpointing into your training process, you can resume your model from the last saved state, and avoid losing any progress or data. Moreover, you can use the Vertex AI Workbench user-managed notebooks to create and manage your notebooks instances, and leverage the integration with Vertex AI and other Google Cloud services.

The other options are not optimal for the following reasons:

A) A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with 4 NVIDIA P100 GPUs is not a good option, as it has higher cost and lower performance than the v3-8 TPU. The NVIDIA P100 GPUs are the previous generation of GPUs from NVIDIA, which have lower performance, scalability, and efficiency than the latest NVIDIA A100 GPUs or the TPUs. They also have higher price and lower availability than the preemptible TPUs, which can increase the cost and complexity of your solution.

B) A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with an NVIDIA P100 GPU is not a good option, as it has higher cost and lower performance than the v3-8 TPU. It also has less GPU memory and compute power than the option with 4 NVIDIA P100 GPUs, which can limit the size and complexity of your model, and affect the training and inference speed and quality.

C) A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with a non-preemptible v3-8 TPU is not a good option, as it has higher cost and lower flexibility than the preemptible v3-8 TPU. The non-preemptible v3-8 TPU has the same performance, scalability, and efficiency as the preemptible v3-8 TPU, but it has higher price and lower availability, as it is reserved for your exclusive use. Moreover, since your model is long-running and checkpointing, you do not need the guarantee of the device not being reclaimed by Google, and you can benefit from the lower cost and higher availability of the preemptible v3-8 TPU.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Cloud TPU

Vertex AI Workbench user-managed notebooks

Preemptible VMs

NVIDIA Tesla P100 GPU

The main advantage of implementing machine learning for this business case is that new problematic phrases can be identified in spam posts. This is because machine learning can learn from the data and the feedback, and adapt to the changing patterns and trends of spam posts. Machine learning can also capture the semantic and contextual meaning of the posts, and not just rely on the presence or absence of keywords. By using machine learning, you can improve the accuracy and coverage of your anti-spam service, and detect new and emerging types of spam posts that may not be captured by the keyword list.

The other options are not advantages of implementing machine learning for this business case for the following reasons:

A) Posts can be compared to the keyword list much more quickly is not an advantage, as it does not improve the quality or effectiveness of the anti-spam service. It only improves the efficiency of the service, which is not the primary objective. Moreover, machine learning may not necessarily be faster than the keyword list, depending on the complexity and size of the model and the data.

C) A much longer keyword list can be used to flag spam posts is not an advantage, as it does not address the limitations or challenges of the keyword list approach. It only increases the size and complexity of the keyword list, which can make it harder to maintain and update. Moreover, a longer keyword list may not improve the accuracy or coverage of the anti-spam service, as it may introduce more false positives or false negatives, or miss new and emerging types of spam posts.

D) Spam posts can be flagged using far fewer keywords is not an advantage, as it does not reflect the capabilities or benefits of machine learning. It only reduces the size and complexity of the keyword list, which can make it easier to maintain and update. However, using fewer keywords may not improve the accuracy or coverage of the anti-spam service, as it may lose some information or meaning of the posts, or miss some types of spam posts.

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Machine Learning for Spam Detection

Spam Detection Using Machine Learning