Predictive scorer Infer unveils ‘first account-based behavior scoring’

Infer’s visualization of its new Behavioral Account Scoring

Infer makes its living by generating predictive scores about which individuals and accounts are likely to become or stay customers.

This week, the Mountain View, California-based company enlarged its capabilities with what it described as the industry’s first behavior-only predictive scoring for accounts.

To unpack what that means, first consider that Infer has focused previously on two basic models for its predictive scoring: Account Fit and Behavior.

The Account Fit model scores whether a business is a “good fit” as a customer, based on relatively stable data points like the technology vendors it uses, its job postings and public filings, its business model, its tech tools and other such factors.

The Behavior model had been used by Infer primarily for leads (i.e., people), based on such time-based activities as pages visited on a client’s website, downloading of a white paper on a specific product, responses to an email marketing campaign and other actions.

But matching the two has been problematic, Senior Director of Product Marketing Sean Zinsmeister told me.

This is because the marketing automation platforms with which Infer is integrated and through which its behavioral web data is obtained — Marketo, Salesforce’s Pardot and Oracle’s Eloqua — do not allow for an easy matching of leads’ behavior with customer-fit accounts in Salesforce’s customer relationship management system, the popular CRM that Infer emphasizes.

So Infer developed a behavioral model for accounts with data about what identified leads at those companies do, by building its own system to match leads’ behavior (obtained via marketing automation platforms) with the businesses where those leads work.

The result is the first predictive scoring based entirely on account behavior, Zinsmeister said, adding that other predictive scorers blend “fit” data with behavior to get their account-based ranking.

Infer isn’t blending the two for account scoring, but instead matches the two scores in a matrix (see below) and the highest combo is the company you want to pursue. That is, it matches the account’s Behavior Score that shows if it is “acting like a buyer of your product,” with the previous Fit Score that shows it “looks like a buyer”:

Opinions expressed in this article are those of the guest author and not necessarily MarTech Today. Staff authors are listed here.

About The Author

Barry Levine

Barry Levine covers marketing technology for Third Door Media. Previously, he covered this space as a Senior Writer for VentureBeat, and he has written about these and other tech subjects for such publications as CMSWire and NewsFactor. He founded and led the web site/unit at PBS station Thirteen/WNET; worked as an online Senior Producer/writer for Viacom; created a successful interactive game, PLAY IT BY EAR: The First CD Game; founded and led an independent film showcase, CENTER SCREEN, based at Harvard and M.I.T.; and served over five years as a consultant to the M.I.T. Media Lab. You can find him at LinkedIn, and on Twitter at xBarryLevine.