Skip to main content

Reactivation Rate Model

Sophie Grobman
  • Updated
This article describes the Reactivation Rate model, which helps you understand the likelihood of each churned customer making a purchase.
 

Introduction

Re-engaging customers previously interested in your brand is more cost-effective than putting all your marketing efforts into acquiring brand-new customers or re-acquiring your churned customers. By understanding the probability of each customer reactivating, you will be able to identify how to treat each churned customer with win-back campaigns to improve retention rates.

With the Reactivation Rate attribute, you will be able to:
  • Easily segment customers based on their probability to reactivate
  • Allocate your promotional budget in the most optimal way
  • Detect which customers will return to your business ahead of time to strategize your reactivation campaigns

 

How to Use

The Reactivation Rate model is available as part of your customer profile and can be used to define target groups and explore them in Customer Explorer.

  1. Under the Explore tab, go to Customer Explorer
  2. Click + New Target Group
  3. Name your Target Group and click on + Selection
  4. Click on Conversion Rate
  5. Select segments from Highest to Lowest you want to target
Optimove will proactively segment clients based on their likelihood of reactivating into five levels: Highest, High, Medium, Low, and Lowest. These groups are measured as a percentile: meaning each group is compared to the other groups from the same set of customers.
 

Get your customers back to business

Instead of guesstimating which of your churned customers require some extra groundwork to win them back, you can now select the ‘Highest’ to ‘Lowest’ segment in the Reactivation Rate criteria. 

To optimize your reactivation campaigns, offer promotions on a sliding scale based on a customer's probability to reactivate. For example, if you are launching a win-back offer, you can send lower promotions to customers with a high probability to reactivate and give customers with a lower probability an extra nudge with a higher promotion. 
 
To further improve profitability, segment customers that have a low likelihood to reactivate and a high future value prediction to focus your resources on revenue-maximizing campaigns.
 

Using Additional Attributes

a) Reactivation Probability Score

This attribute allows you to segment customers based on their predicted likelihood to reactivate.

You can customize the value range to focus on customers with higher or lower chances of re-engagement, and tailor your campaigns accordingly.

Examples:

  • Reactivation Probability Score >= 0.6 will target customers with a 60% or higher likelihood of returning.
  • Reactivation Probability Score < 0.3 could identify churned customers for a more aggressive reactivation offer.

 
b) Rank in Reactivation Probability

This attribute assigns customers a percentile ranking based on their Reactivation Rate score, compared to all other customers in the same model.

This lets you build segments relative to the overall customer base.

Examples:

  • Rank in Reactivation Probability = 100 will segment the top 1% most likely to reactivate.
  • Rank in Reactivation Probability >= 75 will capture the top 25% in terms of reactivation potential.

These segments are ideal for prioritizing limited-budget campaigns or creating tiered retention strategies.

 

Understanding the Reactivation Rate model

The Reactivation Rate attribute is an AI-generated predictive metric that is measured for every customer in your database in the churned lifecycle stage.

Our Machine Learning models look back at historical data, analyze the common behaviors, attributes, or signals of customers that were either converted or reactivated, and use this data as input to the prediction model.
 
Our models look at every relevant data point, from frequency and recency of visits/purchases/deposits, monetary values (purchase/deposit amount), as well as demographic information. As a result, our Machine Learning can analyze the behaviors that led to a customer reactivating and detect churned customers that mirror these behaviors ahead of time to determine their reactivation probability.
 
This metric is updated daily and signifies the likelihood of a churned customer reactivating in the next two periods.
 

Related articles