How to use and build a rules based model

Context 

The Rev.Up platform allows you to build an unlimited amount of rules based models. This article covers what a rules based model is and some example uses for it. 

What is a rules based model? 

A rules based model allows you to create your own custom scoring model. In the rules based model wizard you are able to build segments and then apply a rating to that segment. Like other models, once the rules-based model is published the rating can be used elsewhere in the platform to build audiences to include in campaigns. 

What is a good use case for a rules based model? 

Rules based models are useful for multiple reasons. Some examples of when you want to use a rules based model are below:

1. When you have an idea for how you want to segment your audience in a consistent way and do not want to duplicate the segmentation logic again and again. This is most useful when you are experimenting with engagement models. 
   • Use Case Example 1: 
     • Bombora intent topics in Rev.Up are given a High, Medium or Low value. A customer wanted to consistently use these values in many segments without creating the logic over and over again in each segment. In order to achieve this, they built a rules based model with the logic of: 
       • All accounts with an intent topic that is high are given a score of A 
       • All accounts with an intent topic that is medium are given a score of B 
       • All accounts with an intent topic that is low are given a score of C 
     • Result: The models evaluates the criteria every day and accounts that have changing intent will be given a new rating This allows for the ratings to be used in multiple segments and always have the most up to date audience membership. 
   • Use Case Example 2: 
     • Another example of a rules based model being used to score accounts based on engagement with your company is using opportunity in the model. One customer built a model that segmented accounts based on the number and stage of opportunities. The criteria of the model were: 
       • All accounts with an no opportunities or an opportunity in a late stage were scored as A; this allows the customer to ensure they can pay special attention to prospects with no opportunities 
       • All accounts with an opportunity in a later stage were given a rating of B
       • All accounts with an opportunity in an early or middle stage were given a rating of C 
   • Use Case Example 3: 
     • Another example of a rules based model being used to score accounts based on engagement with your company is using web visit data and intent data in the model. One customer built a model that includes visits to specific product web pages and intent for specific topics. This model can be used to create rules based models that are product specific. 
       • All accounts with intent or visits to the web page that relate to a specific product or solution are given a rating of A 
       • All other accounts were given a rating of F 
   • Result: The models evaluates the criteria every day and accounts that have changing intent will be given a new rating This allows for the ratings to be used in multiple segments and always have the most up to date audience membership. 
2. When you do not have enough data to be able to build a AI machine learning model. 

• • Some times there is not enough data to be able to build a AI machine learning model. This happens when the product or service you are trying to sell is new and there are not enough success events to be able to build a model. 

Considerations for using rules based models

• The output of a rules based model is a rating of A - F
• Rules based models can only be used to score accounts
• An account record will always be given the highest rating that it qualifies for. An account cannot qualify for two ratings. 
• Any attribute that can be used to build a segment can be used to build a rules based model 
• Rules based models are not predictive in the sense that they are not using machine learning to score and apply ratings to records 
• Once a rules based model is published the ratings for the model can be used as an attribute in any other segment you build