You are developing a model to help your company create more targeted online advertising campaigns. You need to create a dataset that you will use to train the model. You want to avoid creating or reinforcing unfair bias in the model. What should you do? Choose 2 answers
Correct Answer: C,E
To avoid creating or reinforcing unfair bias in the model, you should collect a representative sample of production traffic to build the training dataset, and conduct fairness tests across sensitive categories and demographics on the trained model. A representative sample is one that reflects the true distribution of the population, and does not over- or under-represent any group. A random sample is a simple way to obtain a representative sample, as it ensures that every data point has an equal chance of being selected. A stratified sample is another way to obtain a representative sample, as it ensures that every subgroup has a proportional representation in the sample. However, a stratified sample requires prior knowledge of the subgroups and their sizes, which may not be available or easy to obtain. Therefore, a random sample is a more feasible option in this case. A fairness test is a way to measure and evaluate the potential bias and discrimination of the model, based on different categories and demographics, such as age, gender, race, etc. A fairness test can help you identify and mitigate any unfair outcomes or impacts of the model, and ensure that the model treats all groups fairly and equitably. A fairness test can be conducted using various methods and tools, such as confusion matrices, ROC curves, fairness indicators, etc. References: The answer can be verified from official Google Cloud documentation and resources related to data sampling and fairness testing. * Sampling data | BigQuery * Fairness Indicators | TensorFlow * What-if Tool | TensorFlow
Question 32
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?
Correct Answer: A
* 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. References: * 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 33
You work on a growing team of more than 50 data scientists who all use AI Platform. You are designing a strategy to organize your jobs, models, and versions in a clean and scalable way. Which strategy should you choose?
Correct Answer: C
https://cloud.google.com/ai-platform/prediction/docs/resource-labels#overview_of_labels You can add labels to your AI Platform Prediction jobs, models, and model versions, then use those labels to organize resources into categories when viewing or monitoring the resources.
Question 34
You are building a real-time prediction engine that streams files which may contain Personally Identifiable Information (Pll) to Google Cloud. You want to use the Cloud Data Loss Prevention (DLP) API to scan the files. How should you ensure that the Pll is not accessible by unauthorized individuals?
Correct Answer: D
The Cloud DLP API is a service that allows users to inspect, classify, and de-identify sensitive data. It can be used to scan data in Cloud Storage, BigQuery, Cloud Datastore, and Cloud Pub/Sub. The best way to ensure that the PII is not accessible by unauthorized individuals is to use a quarantine bucket to store the data before scanning it with the DLP API. This way, the data is isolated from other applications and users until it is classified and moved to the appropriate bucket. The other options are not as secure or efficient, as they either expose the data to BigQuery before scanning, or scan the data after writing it to a non-sensitive bucket. References: * Cloud DLP documentation * Scanning and classifying Cloud Storage files
Question 35
You are an ML engineer at a manufacturing company You are creating a classification model for a predictive maintenance use case You need to predict whether a crucial machine will fail in the next three days so that the repair crew has enough time to fix the machine before it breaks. Regular maintenance of the machine is relatively inexpensive, but a failure would be very costly You have trained several binary classifiers to predict whether the machine will fail. where a prediction of 1 means that the ML model predicts a failure. You are now evaluating each model on an evaluation dataset. You want to choose a model that prioritizes detection while ensuring that more than 50% of the maintenance jobs triggered by your model address an imminent machine failure. Which model should you choose?
Correct Answer: C
The best option for choosing a model that prioritizes detection while ensuring that more than 50% of the maintenance jobs triggered by the model address an imminent machine failure is to choose the model with the highest recall where precision is greater than 0.5. This option has the following advantages: * It maximizes the recall, which is the proportion of actual failures that are correctly predicted by the model. Recall is also known as sensitivity or true positive rate (TPR), and it is calculated as: mathrmRecall=fracmathrmTPmathrmTP+mathrmFN where TP is the number of true positives (actual failures that are predicted as failures) and FN is the number of false negatives (actual failures that are predicted as non-failures). By maximizing the recall, the model can reduce the number of false negatives, which are the most costly and undesirable outcomes for the predictive maintenance use case, as they represent missed failures that can lead to machine breakdown and downtime. * It constrains the precision, which is the proportion of predicted failures that are actual failures. Precision is also known as positive predictive value (PPV), and it is calculated as: mathrmPrecision=fracmathrmTPmathrmTP+mathrmFP where FP is the number of false positives (actual non-failures that are predicted as failures). By constraining the precision to be greater than 0.5, the model can ensure that more than 50% of the maintenance jobs triggered by the model address an imminent machine failure, which can avoid unnecessary or wasteful maintenance costs. The other options are less optimal for the following reasons: * Option A: Choosing the model with the highest area under the receiver operating characteristic curve (AUC ROC) and precision greater than 0.5 may not prioritize detection, as the AUC ROC does not directly measure the recall. The AUC ROC is a summary metric that evaluates the overall performance of a binary classifier across all possible thresholds. The ROC curve plots the TPR (recall) against the false positive rate (FPR), which is the proportion of actual non-failures that are incorrectly predicted by the model. The AUC ROC is the area under the ROC curve, and it ranges from 0 to 1, where 1 represents a perfect classifier. However, choosing the model with the highest AUC ROC may not maximize the recall, as the AUC ROC is influenced by both the TPR and the FPR, and it does not account for the precision or the specificity (the proportion of actual non-failures that are correctly predicted by the model). * Option B: Choosing the model with the lowest root mean squared error (RMSE) and recall greater than 0.5 may not prioritize detection, as the RMSE is not a suitable metric for binary classification. The RMSE is a regression metric that measures the average magnitude of the error between the predicted and the actual values. The RMSE is calculated as: mathrmRMSE=sqrtfrac1nsumi=1n(yihatyi)2 where yi is the actual value, hatyi is the predicted value, and n is the number of observations. However, choosing the model with the lowest RMSE may not optimize the detection of failures, as the RMSE is sensitive to outliers and does not account for the class imbalance or the cost of misclassification. * Option D: Choosing the model with the highest precision where recall is greater than 0.5 may not prioritize detection, as the precision may not be the most important metric for the predictive maintenance use case. The precision measures the accuracy of the positive predictions, but it does not reflect the sensitivity or the coverage of the model. By choosing the model with the highest precision, the model may sacrifice the recall, which is the proportion of actual failures that are correctly predicted by the model. This may increase the number of false negatives, which are the most costly and undesirable outcomes for the predictive maintenance use case, as they represent missed failures that can lead to machine breakdown and downtime. References: * Evaluation Metrics (Classifiers) - Stanford University * Evaluation of binary classifiers - Wikipedia * Predictive Maintenance: The greatest benefits and smart use cases
