View analytics for experiments with optimized testing

You can view how variants are performing against each other within 24 hours of starting the experiment. Sitecore Personalize processes the analytical data every 24 hours at 4 AM Coordinated Universal Time (UTC) time. Sitecore Personalize finishes processing the analytical data within one hour, at approximately 5 AM UTC time.

An experiment with optimized testing enabled allocates guests to variants and does not take into account unique guests. Sitecore Personalize calculates variant performance based on the primary conversion goal you add to the web or interactive experiment. Performance results are based on the number of sessions and not the number of unique guests who were shown the variant.

To view experiment analytics:

On the navigation menu, click Experiments > Web to see analytics for a web experiment. Alternatively, click Experiments > Full Stack to see analytics for an interactive experiment.
On the navigation menu, click Experiments. The experiment list displays.
Click the Live tab. To refine the list further, click Web, Interactive, or Triggered, to display experiments by type.
Click the name of the experiment you want to view. The Performance screen displays.

Here's a partial image of the upper part of the Performance screen. See the following table for corresponding descriptions of the screen items.

Viewing performance of an optimized test.

The following table contains a description of each screen element on the upper part of the Performance screen.

Screen item	Description
Name	The proper name of the experiment you are viewing.
Analyse & Export	Click to access business intelligence capabilities to further explore the data and create insights.
Tag	Click to apply a tag to the experiment. This is optional.
Status	The current status of the experiment. The current status affects the Status change button.
Status change button	Enables you to change the current status of the experiment.
Preview or Test button	Click Preview to test and preview a web experiment. The Test button only displays for interactive experiments. To test and configure the API response for an interactive experiment, click Test.
Vertical Ellipsis	Click to duplicate, delete, or view the experiment history of the experiment.
Schedule	The date and timestamp of when the experiment started running.
Build	Click to view the configuration of the experiment.
Performance	The Performance screen is selected by default when you open an experiment with a live status.
Operational	Click to view operational metrics for the experiment.
Details	Click to view details of the experiment including when it was created and who created it.
Started	The date the experiment started.
Primary Goal	The name of the primary goal. The primary goal is the metric that the variants are measured against.
Variant Name column	The name of each variant in the experiment.
Primary goal column	The conversion rate of each variant against the primary goal. The primary goal is the metric that the variants are measured against. To see the error range for the conversion rate, hover over the variant bar. The error range provides a visual guide and is not used in any multi-armed bandit calculations or algorithms.
Optimised Allocation	The percentage of traffic that was dynamically allocated to the variant.
Variant bar chart	You can see which variants have higher conversions, based on performance against the primary goal. The primary goal is the metric that the variants are measured against. You can also compare the performance metrics of all the variants in the bar chart.
All Goals By Session table	View the performance of all your variants against all goals.
Variant column	Contains a row for each variant in the experiment.
Sessions column	The number of current unique sessions.
Primary Goal column	The performance metric of each variant against the primary goal. The primary goal is the metric that the variants are measured against.
2nd Goal column	The performance metric of each variant against a secondary goal. A secondary goal is not a metric that the variants are measured against when dynamically allocating traffic.
3rd Goal column	The performance metric of each variant against a tertiary goal. A tertiary goal is not a metric that the variants are measured against when dynamically allocating traffic.
Conversion Gain Versus Standard AB Test	This line graph shows the estimated conversion gain from running an experiment with optimized testing versus an A/B test with manual traffic allocation. The y axis displays the number of extra conversions that occurred from running an experiment with optimized testing enabled. The x axis displays the dates the experiment has run.
Variant Weight Over Time	This line graph shows the variant weight over time, as the multi-armed bandit calculation dynamically allocates traffic.

The following table contains a description of additional elements of the lower part of the Performance screen.

Screen Item	Description
Breakdown by Goal	This line graph lets you compare the performance of all variants against a goal. Click the goal whose metrics you want to see on the line graph, from the drop-down list.
Device	Click the Device you want to filter by. The line graph refreshes to only show metrics for the selected device. This is set to ALL by default.
Time	Select the time span by which you want to filter results. You can select Last 7 Days or Last 30 Days. This is set to ALL by default.
Value	The y axis displays the metric that the variants achieved, as measured against the selected goal.
Date	The x axis displays the date range that you want to view results for, based on what you selected from the Time filter.
Details table	Contains metrics on all variants as measured against the goal you clicked from the Breakdown by Goal drop-down list.
Variant Name column	The name of each variant in the experiment.
Sessions column	The number of current unique sessions.
Selected Goal column	Contains the metrics of the goal you clicked from the Breakdown by Goal drop-down list.
Goal Metric column	Shows a metric related to the goal you clicked from the Breakdown by Goal drop-down list. In this example, the conversion goal shows the Uplift % column. The uplift percentage is the percentage difference in conversion rate between the control and variant.

Do you have some feedback for us?

If you have suggestions for improving this article,