When you define a data monitor, you specify a schedule
on which it should run. Additionally, you can specify a threshold for the
rate of data drift and an operator email address for notifications if this
threshold is exceeded. Data drift and monitoring
works by running a comparison at
scheduled frequency and calculating data
drift metrics for the features in the data set
that you want to monitor. You can define a schedule to run every day, week, or month. Data drift is measured using
a calculated magnitude of change in the
statistical distribution of feature values over time. You can expect some
natural random variation between the baseline
and target datasets, but you should monitor
for large changes that might indicate
significant data drift. You can define a threshold for data drift magnitude
above which you want to be notified and configure alert
notifications by email. For example, using Python code, you can schedule a data drift
monitor to run every week and send an alert if the drift magnitude
is greater than 0.3.