When creating Enterprise models our data scientists will write brand new algorithms based on your specific needs or wants. If and when you need these models built, our data science team will work closely with you to have an incredibly personalized experience. As the model is built, you’ll gain a greater understanding of the deliverables you’ll receive along with a clearer timeline. These models are intended for our for-profit clients. And, if you require a different model or have a different need to be addressed, our team is willing to work with you to come up with a solution not listed here as well. 

This article will cover:

  • What is your goal?
  • What we need from you
  • Example Models
  • Reading the results

What is your goal?

All you need is a question and a large enough sample on which the model should be based. With those ingredients, we can build a model to answer just about any need. 

What WE need from you:

To generate a Customer Lifetime Value model, users must submit a list of clients or customers, along with a client transaction file on each of the individuals/profiles you want modeled.

For enterprise models, you can send our data scientists as much data as you’d like! Unlike some other models, which only allow you to use up to 6 attributes, our team will utilize the full breadth of information you have on your customers.

For an enterprise model, you can input every attribute in your database into different wealth models. These attributes can include affinity, last transaction duration, total transaction amount, last transaction recency, total giving capacity, and many more. The correlations found between these data points then help you find your next best prospects. These correlations are much more reliable than any one single attribute. 


Example Models:

Acquisition Model

Description: The Acquisition Model will help you predict and identify qualified individuals who are most likely to respond to specific marketing campaigns of yours.

Conversion Model

Description: The Conversion Model will help you predict and identify the qualified prospects who are most likely to convert from a lead to a customer.

Up-Sell/Cross-Sell Model

Description: The Up-Sell (or Cross-Sell) Model will help you predict the qualified existing customers who are candidates for up-sale based on their shopping behavior.

Retention/Churn Model

Description: The Retention (or Churn) Model will help you predict and identify which of your existing customers are most likely to churn.

Clustering Model

Description: The Clustering Model will help you pinpoint a number of distinct groups or unique personas based on customers' characteristics (both from you and within WealthEngine) in order to market to them effectively.

Segmentation Model

Description: The Segmentation Model will help you categorize your customer population based on a client's input to see the difference among groups in order to create an effective marketing strategy.

Reading the results:

Model Output

Once the custom models have been built and they have been compared to your screened list,

your Client Engagement Manager (CEM) will present you with an Executive Summary that takes you through the modeling process and explains exactly what you have gotten in return. You will be able to review the modeled scores themselves in My Profiles via newly added columns in your view of that list, or in a flat file that is sent to you outside of the WealthEngine platform. This will largely depend on the size of your file. 

Your CEM will have already analyzed your results and thus be able to guide you through the process of reading and implementing your model insights. 

Each person in the full screened list will have two new scores:

Model Decile: 

Individuals are ranked and divided into 10 deciles:

Decile 1
Top 10%
Decile 2
Decile 3
Decile 4
Decile 5
Decile 6
Decile 7
Decile 8
Decile 9
Decile 10

Model Score: 

This is a raw number that is statistically adjusted to go from 100 – 1000. The higher the number, the more predictive.

If your file is visible in the My Profiles section of the platform, you will be able to use either of these to easily segment your results as part of a Filter. We strongly encourage you to always focus on the decile, however. The raw score is usually only utilized by clients who have such an enormous list that Decile 1 might include both people with a score of 1000 and a score of 700. This will be very rare, however. In most cases the decile alone will be sufficient and focusing on the minute differences between individual raw scores will not be a valuable use of your time and resources. 

If you aren’t sure where you fit in or are at all overwhelmed, don’t worry – you will be figuring all of this out with your Client Engagement Manager!