最新のProfessional-Machine-Learning-Engineer問題集で試験を準備する

You work for a healthcare organization and need to automate the patient triage process. You want to build a telephony agentic solution using the Gemini Live API to perform human-like conversations with patients and gather necessary patient information. You plan to pilot the solution in Japanese. You need to minimize latency and development time, and ensure high, native-like fluency in the model's responses. What should you do?

• A. Use the Gemini Pro model to automatically select the appropriate language.
• B. Use the Gemini Live API, and configure the language_code field to ja-JP. Include a clear system instruction to respond in the patient's language.
• C. Fine-tune the Gemini Flash model on a dataset of Japanese medical transcripts to ensure native fluency. Deploy this custom model behind the Gemini Live API.
• D. Use Gemini Live API Speech-to-Text functionality to capture the user's input followed by Text-to- Speech streaming processing with Chirp to communicate with the patient in their language.

You are building a model to predict daily temperatures. You split the data randomly and then transformed the training and test datasets. Temperature data for model training is uploaded hourly. During testing, your model performed with 97% accuracy; however, after deploying to production, the model's accuracy dropped to 66%. How can you make your production model more accurate?

• A. Split the training and test data based on time rather than a random split to avoid leakage.
• B. Normalize the data for the training, and test datasets as two separate steps.
• C. Apply data transformations before splitting, and cross-validate to make sure that the transformations are applied to both the training and test sets.
• D. Add more data to your test set to ensure that you have a fair distribution and sample for testing.

Your company recently migrated several of is ML models to Google Cloud. You have started developing models in Vertex AI. You need to implement a system that tracks model artifacts and model lineage. You want to create a simple, effective solution that can also be reused for future models. What should you do?

• A. Use Vertex AI Pipelines for model artifacts and MLflow for model lineage.
• B. Use a combination of Vertex AI Pipelines and the Vertex AI SDK to integrate metadata tracking into the ML workflow.
• C. Use Vertex AI Experiments for model artifacts and use Vertex ML Metadata for model lineage.
• D. Implement a scheduled metadata tracking solution using Cloud Composer and Cloud Run functions.

You are working with a dataset that contains customer transactions. You need to build an ML model to predict customer purchase behavior. You plan to develop the model in BigQuery ML, and export it to Cloud Storage for online prediction. You notice that the input data contains a few categorical features, including product category and payment method. You want to deploy the model as quickly as possible. What should you do?

• A. Use the ML.MULTI_HOT_ENCODER function on the categorical features, and select the encoded categorical features and non-categorical features as inputs to create your model.
• B. Use the TRANSFORM clause with the ML.ONE_HOT_ENCODER function on the categorical features at model creation and select the categorical and non-categorical features.
• C. Use the ML.ONE_HOT_ENCODER function on the categorical features and select the encoded categorical features and non-categorical features as inputs to create your model.
• D. Use the CREATE MODEL statement and select the categorical and non-categorical features.

You built a binary classifier that detects fraudulent insurance claims. Only 0.4% of claims in the dataset are fraudulent. Your model reports 99.6% accuracy, but the fraud investigation team reports that almost no fraudulent claims are being flagged. Investigators have limited capacity, so every case they review must be worth their time. You need to select an evaluation approach that reflects business value. What should you do?

• A. Rebalance the test set by downsampling the majority class until classes are equal, and then report accuracy.
• B. Evaluate the model using the area under the precision-recall curve, and select an operating threshold based on the investigators' review capacity.
• C. Continue optimizing for accuracy, but increase the classification threshold to 0.9.
• D. Evaluate the model using log loss on the full imbalanced test set.