Key feature

  Member Health™


What if you could predict which members are at risk of dropping before their renewal?
member health computer image
Tim O'Toole, SPI / SPFA

"Novi’s Member Health feature provides helpful insights into member engagement and allows us to focus our outreach where it matters most."

Tim O'Toole, Steel Tank Institute/Steel Plate Fabricators Association

How it Works

Member Health™ is a powerful machine learning tool that Novi designed to answer the age-old question – Are my members going to renew?  The proprietary AI model learns from big-picture trends found across all Novi customers, plus the unique traits of your membership. After analyzing nearly 80 data points, each member is given a renewal likelihood status of At Risk, On Track or New Member, along with the top positive and negative signals that influenced that status. 

Member Health How it Works Graphic


SCHEDULE A CALL TO LEARN MORE



Use Data-Driven Insights to Focus Your Efforts 


member health list in Novi

Take Action Where it Matters Most

Filter your lists or pull a report of At Risk members to quickly see who needs the most attention. And since you’ll know long before dues invoices go out, you can spend time building relationships, not just chasing payments.

creating group based on health status

Segment Lists for Proactive Campaigns 

Dynamic groups can be built based on health status to sync directly to Constant Contact or Mailchimp or push to any 3rd party integration tool. Since they're updated in real-time, you always have the most up-to-date lists for personalized renewal and engagement campaigns or proactive phone calls.

Use Warning Signals to Help Guide Action

See which healthy and warning signals (aka positive or negative data points) contribute to the health status of any particular member. You can use these signals to help guide phone conversations, email outreach or decide whether an in-person meeting is needed.

member health signals

Removes Bias From Engagement Scoring


 

Because Member Health™ uses statistically tested machine-learning models, it provides a more objective and accurate view than traditional engagement scoring. It removes the risk of unconscious bias that can occur when staff decide which activities count as engagement and how many points each activity should receive. Instead, data from every member is fed into the model. Through training and backtesting, the model identifies which data points positively or negatively influence a member’s likelihood to renew. With this approach, the model continues to learn and adapt so your insights are always fresh and relevant.

Member Health™ Data Points


Turning Member Health™ Actions into Insights



member health insight action items