Basic LTV prediction model with Python for Ad Revenue Apps

Table of Contents

• What is LTV prediction?
• Is LTV prediction good for Ad Revenue Apps and In-app Purchases (IAP)?
• What is linear regression?
• How is linear regression used in LTV prediction models?
• What will I be able to predict with this use case?
• How does the model work?
• How long does it take to get the predictions?
• What does the dashboard look like?
• What are the benefits of using this model?
• What are the limitations of using this model?
• How can I get started with this model?

What is LTV prediction?

To help companies make better decisions, more and more people are turning to lifetime value (LTV) prediction. In a nutshell, LTV prediction is a method of predicting the total amount of money a customer will spend over their entire relationship with a company. Being able to accurately, and effectively, predict LTV of a given ad or campaign helps mobile marketers make more informed decisions about which ads to run and how much to spend on them.

Is LTV prediction good for Ad Revenue Apps and In-app Purchases (IAP)?

The answer is a resounding yes. By accurately predicting a customer’s LTV, mobile marketers can better target their ads and ensure they are reaching the right people. This leads to higher click-through rates, more conversions, and better ROI. Additionally, by knowing an individual customer’s LTV, mobile marketers can tailor their in-app purchase offers to maximize revenue.

Moreover, since LTV prediction helps mobile marketers better understand their customers and their behaviors, they can create more targeted and effective ad campaigns. This helps them reach the right people and reduces the cost of customer acquisition.

In this use case, we use a basic linear regression to predict LTV for Ad Revenue apps.

Basic Linear Regression to predict LTV for Ad Revenue Apps

Overview

In this use case, you will learn how to predict customer lifetime value (LTV) in python using decoded data from Tenjin’s DataVault. In this model, we will predict Day 7, Day 14, Day 30 and Day 90 LTV using a linear regression model.

What is linear regression?

Linear regression is one of the most widely used and powerful tools in predictive analytics. It is a statistical method used to find the linear relationship between a dependent variable and one or more independent variables. It is used to predict future values of the dependent variable based on the values of the independent variables.

How is linear regression used in LTV prediction models?

In LTV prediction models, linear regression is used to identify the linear relationship between a customer’s current purchasing behavior and their future purchasing behavior. By understanding this relationship, businesses can use linear regression to estimate the future value of a customer.

What will I be able to predict with this use case?

In this model, we use Day 0, Day 1, Day 2, and Day 3 LTV data from your current campaign to predict Day 7, Day 14, Day 30 and Day 90 LTV in python. The predictions can be made at a campaign, site ID and app level. For this model, you would need access to more granular data from Tenjin’s DataVault, which is a paid product. You can learn more about DataVault and its different use cases here.

How does the model work?

The model uses decoded data in Tenjin’s Datavault from different Mediation Partners or Monetisation channels such as Applovin and Topon for a simple “on-the-fly” Linear Regression Framework. After performing the regression, the data is pushed back into DataVault. This process can be visualised in the graphic below.

How long does it take to get the predictions?

What does the dashboard look like?

Below, you see an anonymised version of the dashboard. Feel free to navigate through the filters.

What are the benefits of using this model?

• This is a simple model that is easily explainable
• It’s also consistent with the 4-Step LTV prediction in Google Spreadsheets use-case

What are the limitations of using this model?

• Right now this model is only valid for Tenjin’s DataVault customers. However, if you are not a Tenjin customer, and would like to use this model for your LTV predictions, then reach out to us.
• The model is computationally expensive and requires more execution time than our advanced models
• This model is also prone to outlier observations
• The predictions for this model require four data points to be function (Day 0, Day 1, Day 2 and Day 3 LTV)

How can I get started with this model?

If you’re interested in running the python script then reach out to us and we can either send you the script or run it for you.