The Custom 4-Pack Modeling Suite allows you to build four different predictive models and is one of our standard packages for modeling. Taking advantage of sophisticated machine learning, you will be able to determine who in your database you should be focusing on for different types of giving. This article will explore what that means in further detail.  

  • Note: The Custom 4-Pack exists outside of the normal platform. You might see models in the platform that have the same names (e.g. Major Gift Model); those are standard, non-custom models. To learn more about our different types of models, see our other modeling resources.

This article will cover:

  • What is this modeling suite?
  • The four models 
    • Major Gift
    • Likelihood to Give
    • Next Ask Amount
    • Planned Giving
    • Swap-in Option: Mid-Level Gift
  • Model Results

What is this modeling suite?

The Custom 4-Pack Modeling suite, if included in your subscription, will allow you to build four different models: the Major Gift Model; Likelihood to Give Model; Next Ask Amount Model; and Planned Giving Model. These are predictive models that will identify who in your database is likely to behave in the way you want (e.g. give a major gift), based on your own constituents and giving history.

In the beginning, you will work with your Client Engagement manager to determine 6 key attributes (3 categorical and 3 numeric) that will be factored into our analytics solution, thus creating a custom formula that is unique to you. It is this formula that makes up the model! The same 6 attributes will be used to generate all four models included in this pack, which means that, even though WealthEngine will build 4 models, they all require the same information and you will only have to submit it to us once. Those special attributes can include any internal data points you might have, such as volunteer status, college degree, events attended/sponsored, membership level, job title, committees they sit on, magazine subscriptions, how the donation was received (e.g. online vs. credit; cash vs. stock), etc.

Once the models have been built and applied to your full list, you will receive new model scores for each that will tell you who you should be targeting for different types of giving.

  • Note: The models in the 4-Pack Custom Modeling Suite typically take about a month to build. For more information on the process, check out our Guide.

The Four Models:

Likelihood to Give Model:

The Likelihood to Give Model allows you to identify the true prospects in your constituency. These are the people who have never given you a gift of any size, but also look likely to do so. 

The model will use a sample of the people who are your active donors to identify non-donors in your list who, based on a complex analysis of the most statistically significant attributes, are likely to behave in the same way. This will help you expand your donor base by identifying new givers.

Major Gift Model:

The Major Gift Model allows you to identify who, among the constituents in your donor base, you should target for major gifts. This is determined based on an analysis of the people who are already supporting you at that level. You will define what a “major gift” means. 

This will help you identify not just the donors who can feasibly give what you would consider to be a major gift – but specifically the ones that look likely to do so. 

Next Ask Amount:

The Next Ask Amount Model allows you to estimate and predict the amount of an individual’s next donation. Utilizing your giving history, their Estimated Giving Capacity, and numerous other attributes, the model will return a score indicating the likely size of your donor’s next contribution, if they are properly cultivated. 

This enables you to focus on an ideal ask amount —one which isn’t too low or too high—ensuring that whatever your organization receives from your donors or prospects will be the largest quantity they’re willing to donate at that time.

Planned Giving Model:

The Planned Giving Model allows you to more accurately pinpoint who’s most likely to include your organization in their planned gifts. This is determined based on an evaluation of characteristics or patterns that are most indicative of your existing planned givers. 

This model can help you score and rank prospects, in order of similarity to the people who are already a part of your legacy program.

Essentially, with the planned giving model, you can easily evaluate who within your database are likely to contribute planned gifts. Not just in general, but to your organization specifically.

Swap-in option: Mid-Level Gift Model

The Mid-Level Gift model is not automatically included in the 4-pack. However, it can be swapped in for one of the standard models. For example, if you are not interested in modeling for planned giving donors, then you can choose to build a Mid-Level Gift Model instead. 

Similar to the Major Gift Model, this will help you determine who, among the donors in your database, are most likely to give a gift within a particular range (e.g. $500 - $3000). The upper and lower limit of that range will be defined by you. 

Model Results:

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!