Considerations for Setting Up Einstein Lead Scoring

General

• At least 1,000 leads must be created in the last 200 days.
• Of the leads created in the last 200 days, at least 120 must be converted to an account and contact.
• (Optional) Of the leads created in the last 6 months (180 days), at least 120 must be converted to an account and contact with an opportunity created at conversion time.

These requirements apply to each segment of leads you create during setup, including the All Leads (Default) segment.

When you score all leads together without creating segments, and you don’t have enough lead conversion data to build your own predictive model, Einstein uses a global model. The global model uses anonymous data from many Salesforce customers. When you accumulate enough lead data, Einstein builds a scoring model with your data and uses the model with the better results.

• Encourage reps to add as much data to their leads as possible. When leads have more data, Einstein Lead Scoring generates better insights.
• Reps must have read access to the Company, Phone, and Email fields on leads.
• Don’t install Apex classes that reference the ScoreIntelligence field until after you enable Einstein Lead Scoring and receive the notification that enablement is complete. Otherwise, references to the ScoreIntelligence field are invalid.
• Einstein does not use encrypted lead fields in lead score analysis. When you turn encryption on or off for a field, Einstein includes the change in the next analysis. Einstein reanalyzes your leads approximately every 10 days.
• If you turned on Einstein Lead Scoring in Spring ’20 or earlier, you no longer need the Lead filter in the Einstein Lead Scoring Analytics app. To remove the filter, open the Data Manager in Analytics Studio and then click Connect. Click Lead, then Continue. Remove the ScoreIntelligence.Score >= 0 filter text and save your changes.

Scoring Leads in Segments

• Data requirements for scoring all leads together also apply to individual lead segments.
• Each time you change Einstein Lead Scoring settings, Einstein updates the segment IDs for each lead segment, even if you score all your leads in a single segment. During these updates, some data in the CRM Analytics Lead Scoring Dashboard, including lead conversion rates, can be incorrect until Einstein updates your scores based on the new settings.
• When using segments or any other custom lead scoring settings, any new fields added to leads must be added manually to the list of included fields for each segment if you Einstein to consider them during scoring.

Using Filters

If you create lead segments using field filters, be aware of what happens when you delete or deactivate picklist field values.

• If you delete a picklist value from a standard field, you can’t use the value to set up a field filter.
• If you deactivate a picklist value from a standard field, you can’t use it to set up a field filter. However, existing field filters based on that value still work with lead records that contain the deactivated value.
• If you create a field filter using a standard field value and then delete that filtered value from the field, the filter still functions correctly. However, the field appears in Setup with a blank value.
• If you delete a picklist value from a custom field, it still appears in Setup, but any filter created with that value doesn’t function.
• If you deactivate a picklist value from a custom field, it can still be used to set up a field filter.

Field-Level Security

For each lead score, Einstein shows the factors that have contributed the most to the score. The contributing factors that sales reps see alongside lead scores are dependent on the reps’ field access. For example, reps without access to the Annual Revenue field see an error indicating a factor is based on a field to which they don't have access. To resolve this error, make the field accessible to relevant users.