Exam AI-100 topic 4 question 32 discussion

This is a YES if you download the actual code that Microsoft has shared in GITHUB for DP-100 review material https://microsoftlearning.github.io/mslearn-dp100/ you can go to NOTEBOOK "16 - Monitor a Model.ipynb" You need to MODIFY the scoring script and you need to add snippet(s) code of that after you get the prediction of a model you are monitoring, you use application insights to log the prediction. So, answer is yes.

B. No Modifying the scoring file does not meet the goal of monitoring the scoring accuracy of each run of the model. Instead, you can use Azure Machine Learning's monitoring capabilities to monitor the scoring accuracy of each run of the model. You can use the Azure Machine Learning SDK to enable monitoring for your models and configure the metrics to monitor. You can also use Azure Machine Learning's Application Insights integration to monitor the performance and usage of your models. You can use the Azure Machine Learning SDK to log custom metrics and events from your scoring script, and you can use the Azure Machine Learning Studio to view and analyze the logs. You can also use Azure Machine Learning's model explainability features to understand how your model is making predictions and identify potential issues with the model

This is a NO, the solution is to use a DataDrift Monitor: Over time, models can become less effective at predicting accurately due to changing trends in feature data. This phenomenon is known as data drift, and it's important to monitor your machine learning solution to detect it so you can retrain your models if necessary. https://github.com/MicrosoftLearning/mslearn-dp100/blob/main/17%20-%20Monitor%20Data%20Drift.ipynb

The answer is Yes. Open the scoring file and need to add the following code at the top of the file: from azureml.monitoring import ModelDataCollector

You configure Azure Application Insights.