Understanding Pipeline Predict Scores

  • Updated

The Pipeline Predict Score tells you how likely it is that an account will become a pipeline opportunity. This insight tells you which accounts are ripe for targeting, provides insights into pipeline planning, and is a crucial insight in determining when an account is ready for sales outreach.

You can also set up multiple Pipeline Predictive Scores according to account fit and interest in your different product offerings. See Understanding Multiple Predictive Scores for more information.

Screen_Shot_2022-05-18_at_10.33.16_AM.png

How Does It Work?

Pipeline Predict is a machine learning model that looks at past opportunities, learns account properties and activity patterns that are leading indicators of new opportunities being created at accounts, and then identifies those leading indicators in other accounts.

Important: Only Accounts that are NOT in the Pipeline or Customer journey stage will get a Pipeline Predict score. 

Quick Facts

  • Score: >=95 is Highly Likely, >=50 and <95 is Likely and <50 is Unlikely
  • Initial Model Build Time: 24 hours (The model starts running when you click the Save and train model button in Settings > Demandbase-Wide Settings > Predictive Score Setup.)
  • Model Re-Training Time: 24 hours (The model starts running when you click the Save and train model button in Settings > Demandbase-Wide Settings > Predictive Score Setup.)
  • Score Update: Automatic (nightly)
  • Customer Connection Modes:
    • Connected Mode (integrated with Marketing Automation System and CRM) and CRM Hybrid Connection Mode (integrated with CRM): Full scoring capability.
    • MAS Hybrid Connection Mode (integrated with a Marketing Automation System):  Are required to upload a .csv file with opportunities.
    • Disconnected Mode (do not have a Marketing Automation System or CRM integration): Are required to upload a .csv file with opportunities. 

Factors Used When Calculating Pipeline Predict Score

All available data is used, including:

  • Past Opportunities
    • Opportunities (these can still be open, closed/won or even closed/lost) from 10 distinct customers. Use at least 100 opportunities for best results.
    • Recently opened opportunities (past 6 months) are recommended but the date range can be expanded if you have longer sales cycles. 
    • We aren’t excluding all closed/won from training data, only those that are from more than 6 months ago (date range can be expanded if you have longer sales cycles.) 
    • Out of the box settings use opportunity Created Date and entered Pipeline Date fields.  
  • All Activity Logged in CRM (account/contacts/leads)
    • Pipeline Predict uses activity type/category and role. It doesn't use activities details.
  • Engagement Minutes
    • Pipeline Predict uses activities with greater than zero engagement minutes. It doesn't use activities with zero or no engagement minutes. 
  • Sales Inbox/Calendar Events
    • Pipeline Predict uses email open and click and the existence of calendar events. It doesn’t use the title or details in email/calendar events.
  • MAS: All email activity
    • Pipeline Predict uses email open and click. It doesn’t use the title and content.
  • Firmographics
    • Pipeline Predict uses country, state, industry, revenue range, and number of employees. 
  • Trending Intent (daily update)
    • Pipeline Predict uses daily intent signals.
  • Historical Intent
    • Pipeline Predict uses intent behavior up to one year prior to the opportunity creation date. 
  • Known Website Visitors
    • Pipeline Predict uses which job role visits the website and their number of visits. It doesn’t use what pages were visited. 
  • Unknown Website Visitors
    • Pipeline Predict uses the number of anonymous page visits. It doesn't use what pages were visited.

Example

The image below shows an example of how the Pipeline Predict Score is calculated for an account. 

ppexample.png

Top Factors that Determine the Score

To see the Pipeline Predict Score factors, from the left navigation bar, go to Analytics > Dashboard and select an account list from the drop-down list. Scroll down to the Accounts section and hover over the Pipeline Predict tab. In the pop up, click on Learn More About Predictive Model.

Screen_Shot_2022-05-18_at_12.20.10_PM.png

The example below shows some of the Top Factors that determine the Pipeline Predict Score across the accounts. Each account will have different “top factors” that determine its score.

The Likelihood Chart shows the likelihood of accounts generating an opportunity based on the Pipeline Predict model.

Screen_Shot_2022-05-18_at_12.01.52_PM.png

Accessing Pipeline Predict Score Results

After an Administrator configures the Pipeline Predict Score, you can access Pipeline Predict score results.

From the left navigation bar, go to Analytics2.png Analytics > Dashboard and select an account list from the drop-down list. Scroll down to the Accounts section and view the Pipeline Predict tab. This tab shows the accounts recommended using the Pipeline Predict Model. 

Screen_Shot_2022-05-18_at_12.03.03_PM.png

Take Action with Recommended Accounts

You can take action to engage the recommended accounts. For more information, see Taking Action with Accounts and People.

  1. From the Pipeline Predict tab, click See all accounts.
    Screen_Shot_2022-05-18_at_12.03.03_PM.png
  2. On the Engagement page, scroll down to the table and click the Accounts tab.
  3. Select the accounts you want to take action on and click Take Action.
    Screen_Shot_2022-05-18_at_12.04.19_PM.png
  4. Select the action you want to take for the selected accounts. For example, you can create a task in Salesforce to have these accounts assigned to a person on your Sales Team for follow up. 
    Screen_Shot_2022-05-18_at_12.05.00_PM.png

FAQs

Do the scores work out of the box? 

Yes, they are available 24 hours after your CRM and Marketing Automation System (MAS) integrations are enabled and the user clicks the Save and train model button on the Predictive Score Setup page. At least one Keyword Set needs to be created.

To access this page, from the left navigation bar, go to Settings_N.png Settings > Demandbase Wide-Settings > Predictive Score Setup

How long does it take the model to run? 

24 hours

How does Pipeline Predict improve over time?

The model will automatically pick up new signals every night from all available sources.

How does the Pipeline Predict Score know which Personas/Titles are more relevant? 

The model will decide automatically based on all the data plus the “level” of the title (CMO → VP → Director → Manager).

How do I see what factors influence the Pipeline Predict Score for a specific account?

On the Pipeline Predict tab, hover over the score labels (e.g. All, Advertising) of the account you want to view.  A window will display-the top factors determining the score for this account.

Screen_Shot_2022-05-18_at_12.06.26_PM.png

Are Pipeline Predict Scores dynamic? How frequently do the models change/pick up account activity?

Pipeline Predict is updated for all accounts nightly as new activities appear for each account. The Pipeline Predict Score can also decrease when existing activities become stale.

How often does Demandbase recommend that I retrain the Pipeline Predict Score Model? 

Retrain the model every 6 weeks.

Was this article helpful?

9 out of 9 found this helpful