Estimated future DAU

This article teaches you how to use DAU and APRU to achieve user growth through several simple cases. Of course, this article is recommended for those who want to increase the number of users for their account but don’t know where to start.

When planning monthly, quarterly and annual key performance indicators, we often face a series of questions.

For example, how much " DAU " can be achieved? How much new and active user retention can be achieved? And the stability of " ARPU " and other issues.

Many students are confused when faced with these uncertainties in the future.

It seems that there is no way to start with these key indicators.

Before we start this episode, I would like to ask you a few questions:

• “Assuming you add 1 million new users per month, what DAU level can you achieve after one year?”
• "If I give you 10 million in funding, to what extent can you expand your product?"
• “How many new users do we need every day to maintain our goal of 1 million DAUs ?”
• “If the current number of new users remains the same, how much does the retention rate need to increase to reach this goal?”

I'll give you three seconds to think about it. I'd like to hear your answers. You can leave them in the comment section below.

3, 2, 1

Ok , but what I want to say is that the answer doesn’t really matter.

These problems all involve predicting the future of the product and estimating future product trends based on the current level. The data indicators involved are affected by many factors, such as market size, product characteristics, marketing strategy, user life cycle, competing products, technical limitations and many other uncertain factors.

So there is no standard answer.

In fact, when you encounter these problems, you can think about them in a different way.

These questions are actually asking:

• How much can I achieve? " Seeking a definite goal "
• How to arrange the rhythm of customer acquisition? " Determine the method of doing things "
• How much time do I have left? " Determine the time cost "

In fact, it all comes down to lack of confidence, uncertainty, and even a lack of knowledge about this matter.

In order to better cope with these challenges, this issue shares with you a model for predicting DAU . It is simple and practical, based on Excel tools , and can be predicted through data analysis and trends.

Regarding the cost of time, as an entrepreneur, if you don’t want to waste a few years of your life creating something that no one wants to use, you must decide to who you will dedicate the next few years of your life to.

Glossary:

「DAU, daily active users」

"ARPU, average revenue per user"

So how do we predict future DAU ?

Before answering this question, we first need to understand the composition of DAU .

Take the DAU on June 3 as an example

DAU on June 3 = New users on June 3 + Retained users on June 2 + Retained users on June 1 + Retained users on June 2 + Retained users on May 31 + … + Retained users on n days and n months

Retention rate reflects a product's ability to retain users and is the most core indicator of a product.

After understanding the composition of DAU , we can make an estimate of future DAU .

Prepare a set of data samples, generally 1 day retention, 2 days retention, 3 days retention, 4 days retention, 5 days retention, 6 days retention, 7 days retention, 14 days retention, and 30 days retention. In theory, the more complete the retained data sample, the lower the data error.

The data samples are all random numbers and have nothing to do with actual business.

Draw a scatter plot based on the data sample. When using the scatter plot to set a trend line, you can use exponential, linear, logarithmic, power function, etc. to fit the curve. Generally, power function is used more frequently. After confirming the type of function, get the formula through EXCEL , substitute the estimated number of days to calculate the retention rate, then check the display formula to display R² and get the calculation formula.

The closer R² is to 1 , the better the curve fitting effect is. The final trend graph is as follows

The retained data used in the model: actual values ​​are used when available, and estimated values ​​are used when actual values ​​are not available.

It is estimated that in the future, with certain new additions, DAU will be predicted

Kroll emphasized in "Lean Data Analysis" that daily active users are a vain indicator because they include new users and retention users. It is a confusing mixed indicator that requires the establishment of user analysis of the same cohort. It is best not to use DAU as a company-level strategic indicator.

Author: PM Daming

WeChat public account: PM Daming (ID: 1100051)