Determine likelihood to close with predictive lead scoring

Using predictive machine learning algorithms, HubSpot analyzes your customers to determine the probability that your open contacts will close as customers within 90 days.

The Likelihood to close and Contact priority contact properties help you analyze and segment your contacts based on this predictive lead scoring model. Learn more about these properties:

• Likelihood to close: a score that represents the percentage probability of a contact closing as a customer within the next 90 days based on certain contact properties and activities. For example, contacts with a close probability value of 22 have a 22% chance of closing as a customer in the next 90 days.
• Contact priority: a ranking of contacts evenly distributed into tiers based on their Likelihood to close scores. The options for the property are Very High, High, Medium, Low, and Closed Won, where Very High is most likely to close, and Low is least likely to close. Contacts are grouped based on the following logic:
  • Each tier contains 25% of your contacts based on the Likelihood to close score (i.e. contacts with scores in the top 25% are set to Very High, contacts with scores in the bottom 25% are set to Low, etc.). Because the categories are relative groupings, the range of scores in each tier may shift over time.
  • If a contact's lifecycle stage value is set to Customer, the Contact priority is set to Closed won.

The lead scoring properties are automatically set by HubSpot and cannot be edited. To set values for these properties, HubSpot analyzes the following data:

• Analytics and conversion information (e.g., web page visits, time of last visit, email interactions including clicks, opens, and replies, and form submission events).
• The Lifecycle stage property. If a contact's lifecycle stage value is Customer, the Likelihood to close value will be cleared, and the Contact priority will be set to Closed Won.
• Firmographic information provided by HubSpot Insights about the contact’s company.
• Firmographic information about your business and HubSpot account.
• Interactions logged in the HubSpot CRM (e.g., tracked email clicks, meetings booked).

Please note: HubSpot uses blackbox machine learning to provide predictions. With blackbox machine learning, the input and outputs of the model are known, but it is unknown how the input is transformed into the output. For lead scoring, this means it's not possible to know exactly how each input contributes to a contact’s score. Instead, the focus is on how well the model predicts the likeliness of your leads to close. Learn more about how to use lead scoring in the Understanding HubSpot Lead Scoring HubSpot Academy lesson.