You recently deployed a model to a Vertex AI endpoint. Your data drifts frequently, so you have enabled request-response logging and created a Vertex AI Model Monitoring job. You have observed that your model is receiving higher traffic than expected. You need to reduce the model monitoring cost while continuing to quickly detect drift. What should you do?
To reduce the model monitoring cost while maintaining timely detection of drift, the most effective approach is to decrease the sample_rate parameter in the RandomSampleConfig of the monitoring job. This reduces the percentage of incoming requests analyzed, thereby lowering costs, but still allows for sufficient data to detect drift promptly if set appropriately.
The answer is C, simplest and does not affect the time it takes to detect the drift
C. https://cloud.google.com/vertex-ai/docs/model-monitoring/overview#considerations
C as the sample size will be relative to the traffic and also reduce costs.
I went with C.
Reduced Monitoring Overhead: By decreasing the sample_rate, you instruct Vertex AI Model Monitoring to analyze a smaller percentage of incoming requests. This directly reduces the billing cost associated with monitoring. Fast Drift Detection: A well-chosen sampling rate can still provide enough data to capture significant data drift. Monitoring a smaller sample shouldn't significantly impact your ability to detect drift if it's happening rapidly.
A. DataFlow pipeline with TFDV: While DataFlow pipelines with TFDV can be used for data validation, they require additional development and management overhead compared to simply adjusting the Vertex AI Model Monitoring job configuration. B. Custom SQL script: Custom SQL scripts might not be as efficient or maintainable as the built-in Vertex AI Model Monitoring features. Additionally, it would require manually calculating drift metrics, which can be error-prone. D. Increase monitor_interval: Increasing the monitoring interval reduces the frequency of monitoring checks, potentially delaying drift detection. This is not ideal if data drifts frequently.
fitri001 2 months, 1 week ago A. DataFlow pipeline with TFDV: While DataFlow pipelines with TFDV can be used for data validation, they require additional development and management overhead compared to simply adjusting the Vertex AI Model Monitoring job configuration. B. Custom SQL script: Custom SQL scripts might not be as efficient or maintainable as the built-in Vertex AI Model Monitoring features. Additionally, it would require manually calculating drift metrics, which can be error-prone. D. Increase monitor_interval: Increasing the monitoring interval reduces the frequency of monitoring checks, potentially delaying drift detection. This is not ideal if data drifts frequently.