A preference tag is based on the user behavior table or order list data that is imported or reported. The tag value includes the attribute with the largest number of user occurrences or the largest value, such as the user's preferred shopping time period, price range, channel, theme, or category, and the highest price of a single item purchased by the user.
Example 1:
Create the first three user-preferred categories as tags. The tag name is "Preferred category" and the tag value is a specific category.
The following table lists the number of times that four users purchase the five categories.
User | Category 1 | Category 2 | Category 3 | Category 4 | Category 5 |
User A | 2 | 3 | 1 | 0 | 3 |
User B | 1 | 2 | 2 | 0 | 1 |
User C | 0 | 0 | 0 | 1 | 0 |
User D | 0 | 0 | 0 | 0 | 0 |
Then the result of the "Preferred category" tag is:
User | Preferred category |
User A | Category 2, Category 5, Category 1 |
User B | Category 2, Category 3, Category 1 Note: Category 1 and Category 5 are both ranked 3rd in terms of times and are not null. As a result, Category 1 with the highest serial number is selected. |
User C | Category 4 |
User D | NULL |
For the "Preferred Category" tab, the number of people covered by the tab is 3 (user A, user B, and user C), and the coverage rate is 75%.
For a single specific tag value, for example, the number of people covered by the tag value "category 3" is 1 (user B), and the coverage rate is 25%.
Example 2:
The time when you place an order is divided into four time periods: 0:00 to 6:00 a.m., 6:00 to 12:00 a.m., 12:00 to 18:00 p.m., and 18:00 to 24:00 p.m.. The time period when you place an order most frequently is the label value of the "preferred shopping time" label.
Create a preference tag
Preference labels are based on user behavior tables and order details tables. For more information about data requirements, see Data Table Requirements. For more information about how to import data from user behavior tables and order details tables, see User Behavior and Order Details. For more information about how to report and store order event data, see Event Hub.
If you want to create a time-based preference tag, the time field of the user behavior table and order schedule must be at least up to the hourly granularity.
Steps:
Choose Workspace> User Insight > User Tags > Tag Management.
Click New Tag in the upper-right corner.
In the dialog box that appears, select Preference Tag and click OK.
Configure the parameters in the Basic Information section.
Enter a label name. Click the
icon next to the tag field to customize the tag field name. The prefix is fixed to "user_tag_". If you do not customize the tag field name, the system will generate a field name based on the tag name. Set whether tags are manually updated or automatically updated on a periodic basis. The periodic basis supports daily, weekly, and monthly.
Select a label category. The default category is Unclassified.
Enter a label description.
Configure tag rules.
Select User Behavior. If you create a tag based on user behavior, select a specific behavior type under the Interaction Behavior category. If you create a tag based on order details, select a specific behavior type under the Order Behavior category.
If the selected behavior has multiple data sources, you need to select a source table. If the selected behavior has only one data source, you do not need to manually select a source table.
The behavior time. You can use multiple methods to set the behavior time. For more information, see Time-based.
When you create a tag based on order details, the table may contain multiple time fields. Before you set the behavior time, you must select the corresponding order time field.
NoteIf this parameter is set to a non-specific time, when the tag is updated, the specified time is refreshed based on the update time and the tag is calculated based on the new time. If this parameter is set to a specific time, the updated result remains unchanged unless the behavior record or the order record itself changes.
Other restrictions can be set at the same time. For example, in the preceding figure, additional restrictions are placed on mini programs.
You can click Add Attribute to add a condition. You can specify a maximum of 10 conditions. The relationship between multiple conditions is an AND.
Set preference conditions. Preferences are divided into two types:
Feature: If an attribute has the largest number of behaviors or the largest value, the attribute is used as the tag value. For example, if a user purchases a category the most times, the tag value is the category, as shown in the preceding figure. Alternatively, if a user purchases a product with the highest price, the tag value is the price of the product. Supports the first 1, 3, or 5 statistical results.
Time-by-time preference: The time-by-time statistics of user behavior are divided into time-by-time statistics, and the time-by-time period in which the user behavior has the highest probability is the tag value, as shown in the following figure. You can modify or add or subtract time periods. Time periods cannot intersect.
After the configuration is complete, click Estimate Number of Users in the lower part of the page. On the page that appears, you can estimate the number of users and the coverage rate of each tag.
Click Save. The custom tag is created.
The custom tag that you created is added to the tag list. The tag is in the Executing state. You can use the custom tag only after its status changes to Executed. For more information, see Tag Management.