You are here:
Understand How Einstein Scores Your Opportunities
Learn about the process Einstein uses to predict which opportunities are most likely to be won.
Required Editions
| Available in: Lightning Experience and Salesforce Classic. |
| Available with Sales Cloud Einstein, which is available in Performance and Unlimited Editions, and for an extra cost in Enterprise Edition |
| Available to eligible customers for no extra cost in: Enterprise, Performance, and Unlimited Editions |
Einstein Opportunity Scoring uses data science and machine learning to score your opportunities so that you can prioritize them. By using machine learning, Einstein Opportunity Scoring provides a simpler, faster, and more accurate solution than traditional rule-based scoring approaches.
The Scoring Model
To predict which opportunities are most likely to be won, Einstein analyzes your and your team’s past closed opportunities (both closed-won and closed-lost) to build a scoring model. The criteria used in the analysis includes the following.
- Each opportunity’s record details (both standard and custom fields), history, and related activities
- The related account’s record details and some record history
- Details about the related products, quotes, and price books
During setup, Salesforce admins can choose whether to have Einstein consider all opportunity records and custom fields or only a subset. When Einstein builds the scoring model, the omitted records and fields are ignored.
If you don’t have enough opportunity 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 opportunity data, Einstein builds a scoring model with your data and uses the model with the better results.
Once a month, or whenever the admin updates the settings, Einstein reanalyzes the opportunity data and the model is refreshed. Opportunity scores are updated every few hours.
Factors That Contribute to Scores
For each opportunity score, Einstein shows the factors that have contributed most to the score, both positively and negatively. Sometimes, an opportunity has a score but doesn’t show any factors. This could be because there are too many minor factors for any of them to help understand how the score was calculated. Or, it could be because the factors are complex and, therefore, too difficult to summarize.
Factors are based on your CRM data and accurately contribute to the score, even if they seem counterintuitive. For example, a deal with an enterprise customer requires extra steps, such as legal review and a longer negotiation process. These extra steps delay the close date. But, because the delayed close date signals that the deal is progressing, the delay is associated with a higher score. However, for a deal with an SMB customer that doesn’t include extra steps, a delayed close date is associated with a lower score.
When Scores Don’t Appear
A score might not appear on a particular opportunity for one of these reasons.
- The scores haven’t been calculated yet because Einstein Opportunity Scoring was recently enabled. It can take around 48 hours before scores are available.
- A previously scored opportunity is closed, so the score is removed.
- The admin excluded the opportunity from Einstein’s scoring process. If the opportunity was previously scored, the score is removed.
- The opportunity was added less than six hours ago.
- If Opportunity Scoring was turned on by default, scores aren’t available for opportunities that are related to a person account. To get scores for those opportunities, turn off Einstein Opportunity Scoring and then turn it on again.
When Scores Aren’t Recalculated
A previously scored opportunity is more than three months past its closed date. Einstein gives the opportunity a default score of 5.
