The AB test component can help you make scenario decisions by testing and comparing the effects of scenarios. You can test up to 30 scenarios at the same time.
The specific method of AB test: in order to enable users to achieve the same target event, N schemes are formulated, the users participating in the test are randomly divided into N groups, and the N schemes are applied at the same time. After a period of time, the probability of N groups of users achieving the target event after applying the scheme is counted respectively, and the scheme corresponding to the group with high probability wins.
For example, the same audience is randomly divided into two groups, each 50% users, and different promotional SMS messages are sent to the two groups to test which type of message has higher sales.
To configure a universal filter, perform the following steps:
Click the AB test component and configure it in the panel that appears on the right, as shown in the following figure.
Enter a step name.
Specify the name of the group and the percentage of the number of people in each group. You can click New Group to add a group.
NoteYou can specify 2 to 30 groups. The total number of people in all groups must be equal to 100%.
Set end conditions:
Performs until all users participate in the AB test or until the end of the automated campaign.
After the total number of people entering the AB test reaches the number you specified, the AB test ends. The remaining users no longer randomly enter the group, but all directly enter a definite group.
In this case, you need to choose which group to put the remaining users into:
According to the results of the AB test, the group with the highest achievement rate of the execution target is entered.
Go to the specified group.
Click OK. A blank branch is generated for each group on the canvas and is finally merged to the "Test Target" node, as shown in the following figure.
Set each branch based on your scheme, as shown in the following figure.
You can perform operations on components in branches, such as adding, copying, pasting, and deleting components. However, you cannot add lines to branches.
Click the "Test Target" node and set the test target in the panel that appears on the right, as shown in the following figure.
Specifies the time to wait before determining that a user reaches the target event. You can set a relative time or a specified time.
Relative time: After the user finishes executing the previous component, wait for a period of time before judging. The unit can be minutes, hours, or days.
Specified time: Wait until a specific time point, and make a judgment at this time point.
The following code provides an example on how to configure the Behavior Event component:
NoteUser behavior event data is collected by applications such as apps, mini programs, and web pages and then reported to Quick Audience. For more information, see Event Reporting (New Version) or Event Management (Old Version).
Item
Example value
The source of the event.
For Event Reporting (New Version), select an event source type.
For Use Event Management (Old Vdition), select the name of the event source channel.
Event Name
Select an event.
Restriction Attributes
Supports setting event property requirements.
Turn on the Limit Attributes toggle and set the attribute requirements for the event. Only when the attribute requirements are met, the event is counted as the target.
You can click Add Attribute to add an attribute requirement. Multiple attribute requirements support the,, or relationship. You can click the corresponding text on the left to switch between them.
Limit times
Supports setting the same user to meet the event and attribute requirements multiple times before it is counted as a goal.
Turn on the Limit Times toggle and enter the number of times.
Set the target achievement rate of the plan to compare with the actual target achievement rate of each group after running.
NoteTarget achievement rate=number of users who achieve the target event in the group ÷ number of people in the group × 100%
Choose whether to market based on compliance:
Yes: Generate two groups, "achieved" and "not achieved", and perform different subsequent operations according to whether the user has achieved the goal, as shown in the following figure.
No: All users share a follow-up link, as shown in the following figure.
Click OK. The "Test Target" node is configured.
NoteFor the specified time, if the specified time point has passed when the user enters the "Test Target" node, it does not wait and directly determines.
AB Test Execution Action Analysis
After the AB test component is run, the test target node records the test target achievement status of each group of this execution so that you can select a solution based on the target achievement rate.
As shown in the following figure, the execution data is displayed above the test target node, including the winning group, the total number of targets reached in all groups, and the total number of inflows.
Click the Execution Data section. The Execution Action Analysis panel appears on the right side. The following figure shows the number of inbound users, the number of users who have reached the target, and the target achievement rate for each group. In the figure, since the target achievement rate of the reference group 1 is high, the scheme corresponding to the reference group 1 is recommend adopted.
Since the number of people entering each group may be different, please take the target achievement rate as the main reference index for evaluating the effect of the scheme.
If the end condition of the AB test node is set to the maximum number of users who participate in the AB test, some users may not participate in the AB test that is randomly grouped. In this case, you can select All Users or Test Users in the upper-right corner to display only the data of users who participate in the AB test.
