Revealed: What are the characteristics of the user portrait system of large companies?

In the era of big data, user portraits have become a key tool for precision marketing and product optimization. This article will reveal the characteristics of the user portrait system of large companies, from basic attribute tags, key behavior tags to layered behavior tags and interest preference tags, and analyze in detail how to build a comprehensive and accurate user portrait.

In addition to describing basic information such as gender and age, can user portraits guide operational strategies and output solutions to increase user activity/payment? Of course! However, it must be combined with specific business conditions. A few days ago, a classmate interviewed a large company, but he was busy reciting the RFM index and failed... Let's review the analysis ideas and requirements of large companies for user portraits.

1. Talk about user tags, let’s talk about scenarios first

First of all, each analysis method is limited to specific business scenarios. In essence, the RFM method widely circulated on the Internet is only suitable for high-frequency interactive retail e-commerce business scenarios, such as durable goods, maternal and child care, medical care, health care, games, film and television entertainment, etc., which are not suitable for RFM. Although this student has experience in e-commerce, he overlooked that he was interviewing for a novel reading APP of a certain factory.

The motivation for paying for novels is highly content-driven. If you want users to pay, you must at least have content that makes them happy. If you want users to be happy, you must know what kind of content they like. In addition, novels are different from short videos or live broadcasts. Users' sense of pleasure is not obtained by being instantly stimulated by cool videos, but by the immersive experience during continuous reading.

This forms a gradual immersive conversion process: find content → click to read → continue reading → pay page → pay → continue paying. Therefore, locating the current stage of the user and guiding the user to the next stage is the most critical issue in user portraits. This requires rich user tags and clear user status.

2. Basic attribute tags

Some user tags can be collected using forms. For example:

Maternal and infant products: the month the baby was born and the baby’s health status

Children's education: age, grade, subject (English/Chinese/Olympiad mathematics), purpose

Logistics and freight: cargo type, cargo weight, departure point, destination, time requirements

Housekeeping service: home location, service content (nanny/cleaning/nursing), home visit time

Healthcare: age, gender, physical condition, medical history

Note! These forms are based on the rigid needs of the business itself. For example, without address information, the auntie cannot provide door-to-door service. Therefore, this kind of form information can be understood and cooperated by users, with low collection difficulty and high label accuracy.

In the scenario of novels, it is not suitable to collect data using forms. Because the user's "demand" for novels is not simply 1+1=2. Liking time travel and liking the Three Kingdoms does not mean liking to "travel to the Three Kingdoms". Therefore, when designing a form, there is no need to gossip about every detail, and try to find the key fields. For reading:

1) Gender (there is indeed a big difference between male and female frequencies)

2) Story themes (e.g. fantasy, history, time travel, romance)

3) Are you a fan of a certain author (popular author/classic author)?

It has a great impact on user behavior and is easy to collect, so it can be collected in the form. Other tags need to be obtained through subsequent behavior analysis.

3. Key Behavior Tags

To locate the current stage of the user, you need to find the most critical tags that can distinguish the user type. Since the goal is to increase the payment rate, the payment-related tags are the most important. According to the user's payment record, three states can be distinguished: never paid/paid for one novel/paid for 2 or more books. The guidance direction is also very clear (as shown below)

Note that in the above categories, there is a strategy that guides: keep subscribing to this article. This means that you need to observe the progress of users when reading novels. If the paid novel has been completed/discontinued, you have to recommend new content immediately; if the user can't even finish reading it, or has already abandoned it, you have to find other good content to recommend. Therefore, you have to consider the user's reading behavior tags.

4. Hierarchical Behavior Tags

User reading behavior is of great significance to payment. In theory, only users who are addicted to a novel will pay, and they are likely to pay for more other content they are interested in. Those who have not yet been addicted should be dragged into the novel as soon as possible, and those who have already left the novel should be prevented from leaving. Therefore, it is important to distinguish between the states of not being addicted, being addicted, and being out of the novel (Note: "addiction" is a common name for readers who are addicted to the plot of a novel)

If a user is hooked, the minimum requirement is to have a certain login time and frequency in the novel APP. Therefore, we can use, for example, the number of logins/total login time in the past week to distinguish between light, medium, and heavy users who are active on the platform (as shown in the figure below).

Thirdly, if a user is attracted to a piece of content, he will definitely not browse around, but focus on one piece of content. Then this content will account for a considerable proportion of his active time on the platform.

This can distinguish whether the user focuses on a content label:

No feeling: There is no long-term active content

Dedicated: Have a long-term active content

Boai: There are multiple long-term active contents

To determine how long is long, you need to use the stratified analysis method.

Third, falling into a pit and leaving a pit is a dynamic process. If there was no focused content before, but there is now, it is called falling into a pit; if there was focused content before, but there is no focus now, it is called leaving a pit. Therefore, when constructing labels, we cannot only consider the current state, but also have to associate it with the state of the previous cycle. For example, if we associate it with the previous cycle and find that the user's focus has decreased, then it can be summarized as falling into a pit. If the focus increases, it can be summarized as leaving a pit (as shown in the figure below).

With behavioral labels, combined with payment, we can more accurately distinguish problems. Of course, when formulating strategies, we must also consider the user scale and give priority to meeting the needs of large groups (as shown in the figure below).

When constructing label logic, the MECE method must be followed to avoid accidents. This is the essential difference between how professional data analysts and business personnel think about problems: business personnel can directly grasp the most obvious ones, while data personnel focus on the comprehensiveness and rigor of the situation.

5. Interest Preference Tags

As mentioned above, there are various problems with directly collecting interests. So what else can we do? Of course, we can extract interests from user behavior. If we have made detailed classification and statistics on the reading behavior of users' content in the previous stage, it will be easy to distinguish:

1) Users spend a long time reading XX type of content

2) Users are highly loyal to XX type of topics

3) Users have a high payment rate for XX type of content

By crossing active and paid behaviors, it is easy to define user interest preferences

Of course, there is a type of user who insists on getting something for free, and has many related reading behaviors, but just won’t pay. At this time, you can use coupon testing to distinguish the price-sensitive ones from the real freeloaders, thus forming a price preference label.

6. Output Strategy

With the above basic label preparation, when outputting the final strategy, you can combine various strategies according to user needs just like building blocks. As long as the foundation is laid firmly, the results will be easy to achieve (as shown below)

VII. Summary

Many students are used to working with ready-made datasets on the Internet. Most of the so-called user portraits are ready-made fields, especially those directly collected from form fields. This kind of ready-made dataset is very different from the actual situation, and the most important thing is not practiced: labeling by using user behavior.