Set up Performance Monitors
Performance monitoring reference guide
When To Monitor Performance
Performance metrics quantify a model's effectiveness in its predictions. Monitor performance metrics when deploying a model in production to flag unexpected changes or drops in performance.
Additionally, these metrics are used during the model validation phase, offering insights that guide the improvement and fine-tuning of models to achieve optimal predictive performance.
🏃 Common Questions:
Performance Metrics By Use Case
Metrics are batched into Metric Groups that align with model types and their variants.
How To Monitor Performance
Easily enable, customize, and alert model performance to ensure your production models stay in tip-top shape.
Step 1: Enable Performance Monitors
Monitor how your model performs in production based on metrics applicable to your model use case.
You can enable managed performance monitors automatically and tailor them to your needs or fully customize your monitors.
Using Managed Monitors
Use managed monitors if this is your first time monitoring your model, you want to try a new metric, or you want to simplify your setup workflow!
From the 'Setup Monitors' tab, enable the applicable performance monitors based on relevant metrics for your use case.
Enabled monitors will be represented in the monitors listing page
Step 2: Configure Evaluation Window
An evaluation window defines the period of time your metric is calculated on (i.e. the previous 24 hours). Increase this window to smooth out spiky or seasonal data. Decrease this for your monitors to react faster to sudden changes.
A delay window defines is the gap between the evaluation time and the window of data used for the evaluation. A delay window tells Arize how long to delay an evaluation. Change this if you have delayed actuals or predictions, so you evaluate your model on the most up-to-date data.
Managed monitors create monitors for all applicable features for a given metric with preset basic configurations. Based on the metric and feature monitor you want to edit, edit your monitor's details. These settings apply to all managed monitors of the same type.
Managed Monitors Default Configurations:
Evaluation Window: Last 72 hours
Delay Window: No delay
From the 'Monitors' tab, edit the monitor configurations in the 'Managed Performance Monitors' card.
Step 3: Calibrate Performance Threshold
Arize monitors trigger an alert when your monitor crosses a threshold. You can use our dynamic automatic threshold or create a custom threshold. Thresholds trigger notifications, so you can adjust your threshold to be more or less noisy depending on your needs.
Learn more here about how an auto threshold value is calculated.
Managed monitors create monitors for all applicable features for a given metric with an automatic threshold. If you've had performance issues in the past, we suggest you take a look at the threshold to make sure the threshold is relevant to your needs.
How To Edit Managed Monitor's Threshold In Bulk
Change the tolerance of an existing automatic threshold by adjusting the number of standard deviations used in the calculation in the 'Managed Performance Monitors' card to edit all of your managed monitor auto thresholds in bulk.
Note: this will override any individual managed monitor auto threshold config, but will not change any manual thresholds configured for monitors.
How To Edit Managed Monitor's Threshold Per Monitor
Change the tolerance of an existing automatic threshold by adjusting the number of standard deviations used in the calculation in the 'Monitor Settings' card or create a new custom threshold to update an individual monitor.
From the 'Monitors' page, click on the 'Monitors Listing' to select the monitor you want to edit.
Step 4: Set Notifications
Your Monitor Status provides an indication of your model health. Your monitor will either be:
Healthy: Sit back and relax! No action is needed
No Data: When the monitor does not have recent data in the evaluation window
Triggered: When your monitor crosses the threshold value, indicating a model issue
When a monitor is triggered, get notified when your model deviates from your threshold. You can send notifications via e-mail, PagerDuty, OpsGenie, or Slack. Learn more about notifications and integrations here.
All managed monitors will be set with the default configuration of 'No Contacts Selected'. To get the most out of Arize, set notifications so you are automatically notified when your monitor is triggered. You can edit notifications in bulk edit notifications per monitor for enhanced customizability.
How To Set Managed Monitors Notifications In Bulk
Configure performance monitor notifications for all managed monitors for an easy way to fully set up monitors in Arize.
How To Edit Managed Monitor's Notifications Per Monitor
Set notifications per monitor to limit notifications, change alerting providers or add individual emails to the alert. Within each monitor, you can add a note and edit the monitor name to better suit naming conventions you may already have.
From the 'Monitors' page, click on the 'Monitors Listing' to select the monitor you want to edit.
Last updated