Mind your metrics
The programs anomaly detection model watches several key metrics that are reliable measures of customer engagement. Over time, the model “learns” what to expect from each program. When it spots something unexpected, either a spike or a drop, it reports the activity as an anomaly.
The model evaluates program results nightly and displays dates and times using Greenwich Mean Time (GMT). It updates values and charts for each program metric after the analysis is complete. You can view a history of results over the past 7, 30, 90, or 450 days.
After a program has run long enough for the system to understand expected program behavior and recognize anomalies, the system reports anomalies within one day of observing an anomaly. Typically, it takes approximately 2 weeks after activating a program to begin reporting behaviors and anomalies.
Each metric type indicates summary results observed for all emails currently running in the program.
Emails sent
This metric measures the program’s outbound mailing activity. It is the sum of all email messages that were sent during the previous day by all emails currently running in the program.
Opens (unique)
The Opens (unique) metric is a good indicator of how customers are responding to the program. It identifies the total number of email messages associated with the program that have been opened at least once. Each open is counted only once per email recipient.
If an email recipient opens an email message three times, the system records a single unique open. However, if three different email recipients each open the same message once, the system records three unique opens.
The system uses a tracking pixel to determine the number of times that an email message is fully opened or displayed in a preview pane. The message is considered opened even if the recipient blocks images or clicks an unsubscribe link.
Clicks (unique)
Are your customers interested in the emails that the program sends? This metric shows you how many email recipients are interested enough to do more than simply open the email. This metric identifies the total number of email recipients who have clicked at least one link in any of the email messages sent by emails in the program.
If a single email recipient clicks on three links in the same email, the system records one unique click. If the same individual clicks one link in three different email messages, the system records three unique clicks.
Hard bounces
This metric indicates problems that prevent you from reaching customers through the program. This metric refers to email messages that are undeliverable because of a permanent characteristic of the message or delivery address, such as a misspelled or non-existent email address.
Soft bounces
The Soft bounces metric tells you about delayed messages. It refers to email messages that are currently undeliverable because of a temporary characteristic of the message or delivery address, such as a full inbox or system delays. This type of anomaly might be crucial to spot if the email is time-sensitive, such as a notification of a limited-time discount offer.
Unsubscribes
Watch this metric closely to spot customers who don't want to hear from you anymore. The Unsubscribes metric indicates the total number of requests to stop receiving email messages sent by any of the emails currently running in the program. Anomaly spikes here usually indicate a need for a quick response.