Predictive Insights using Backup Models

Learn how Einstein for Nonprofits uses Backup Models to generate predictive insights for your org.

Backup Models provide metrics on the likelihood of constituents becoming first-time, recurring, or top donors. Backup Models provide predictive metrics even when your org doesn’t meet data thresholds for Einstein Prediction Builder (EPB) to generate your metrics. EPB needs a minimum threshold of records to be able to generate predictions. Einstein for by Nonprofits informs you via the notification bell when your org meets this threshold.

Backup Models use a set of calculations specific to your org to generate scores. If Backup Models are enabled at the same time as EPB, then the generated EPB results appear on the Contact cards. You should set up Backup Models at the same time as EPB.

Backup Models produce percent probability scores similar to those generated by EPB. However, for higher accuracy and org-specific customized output, Salesforce recommends that you use data from your org to obtain EPB predictive insights.

The status of an EPB job shows Model Failed when EPB fails to generate a prediction. If EPB is unable to model the data set and generate scores due to insufficient data volumes or an application error, then the results from Backup Models appear on the Contact cards instead. Ensure that Backup Models are enabled for your org. Failure to activate Backup Models may result in a lack of predictive insights for your Contact cards.

Backup Models include constituents data, except Contacts that are set to Don't Profile. The Don't Profile field is located on the Individual record that the Contact is associated with and it ensures that the user's data is not used for future modeling.

Similar to EPB, Backup Models also analyze data to compute scores for three predictions:

• Likelihood to become a first time donor: Provides fundraisers with insight about supporters who have no previous donations, but can possibly be converted to donors.

• Likelihood to become a recurring donor: Provides fundraisers with insight about supporters who can probably be converted to repeat donors.​ If a contact has a recurring donation record with Status "Active" and Recurring Type "Open", then that contact is a recurring donor.

• Likelihood to become a top donor: Provides fundraisers with insight about constituents who have donated enough over the past three years to move them past the top donor threshold.​ The top donor threshold is calculated as follows:

  1. Consider all contacts who donated two years ago. Among these, find the giving threshold for the top 25% of donors from two years ago and refer to this group as the "two years ago threshold".

  2. Consider all of the contacts who donated last year. Among these, find the giving threshold for the top 25% of donors from last year and refer to this group as the "last year threshold".

  3. For each contact, if any of these are true, that contact is considered a top donor:

     • ​​A contact's giving for the last two years is greater than the two year threshold. ​

     • A contact's giving this year is greater than the last year's threshold.

     • A contact's giving last year is greater than the last year's threshold.

You can enable or disable any of these models. By displaying Backup Models predictive insights on Contact cards, these metrics are visible to users within the nonprofit.

The set of input fields used by Backup Models has been selected by Salesforce.org after careful study of opt-in customer research and ethical data considerations. The set of fields that are used as model inputs is different for each predictive field. The automated process determines which of the set of model input fields to use in your org’s model, and what relative influence each field has on the model’s output. Each model is an arithmetic and logical formula. It is impossible to extract any aspect of user data from the Backup Model.

You will need to ​set up Backup Models to generate predictions​ and display insights​.