Skip to content
Home » Sales App: Lead Predictive Scoring

Sales App: Lead Predictive Scoring


Predictive lead scoring uses a predictive machine learning model to calculate a score for open leads based on historical data. The score helps sellers prioritize leads and achieve higher lead qualification rates, and reduces the time it takes to qualify a lead. The out-of-the-box model in D365 sales chooses the top factors that influence the score. The model assigns a score between 0 -100 to leads based on the signals from leads and related entities, such as contact and account. Using these scores, you can identify and prioritize leads that have a higher chances of converting to opportunities. The score will be calculated shortly after saving or importing a new lead; refresh the lead page to view the score.

*Note that Predictive Lead Scoring is an Advanced Sales Insights feature.

In Dynamics 365

Once enabled predictive lead scoring will be visible on the My Open Leads Scored system view. The view displays your list of leads including lead score, grade and scoring trend.

  1. Score shows the likelihood, on a scale of 1 to 100, that the lead will convert to an opportunity. Scores are refreshed after every 24 hours.
  2. Score Trend shows the direction in which a lead is trending. Trends are calculated by comparing the current lead score with the previous score.
  3. Grade ranks leads based on the generated score. System administrators can define lead score ranges for a grade, depending on your organizational requirements.

In forms, the Lead score widget (below) displays the top positive and negative reasons that influence the score:

  1. This section displays information such as lead score, grade and trend.
  2. This section displays the t reasons, both positive and negative, that affect the lead score. (The Lead score widget displays only the top five positive and negative reasons. To view all the positive and negative reasons that are affecting the lead score, select details)
Scoring Models

A scoring model defines the criteria for choosing leads for training and scoring. If your organization follows different sales practices across different regions or business units, you can create models and unique training sets for each of them. You can create up to 10 models, both published and unpublished, for different sets of leads. The Sales app warns you if you try to create a model that might score the same leads as an existing model.

License and Prerequisites
LicenseDynamics 365 Sales Premium or Dynamics 365 Sales Enterprise
  • Advanced Sales Insights features must be enabled. You then need to use the standard lead entity.
  • You need to have enough leads to train the model based on past data. Your organization must have created and closed at least 40 qualified and 40 disqualified leads during the time frame selected in the Train with leads from the past field of the scoring model. The time frame ranges from three months to two years. The more leads you can include to train the model, the better the prediction results will be.