Skip to main content

Understanding how Persado Scores your Content

Persado scores your content for performance and compliance to help you determine what to put into market.

A
Written by Amy Blakemore
Updated over a month ago

A key checkpoint in every Create project is reviewing LoFi previews in Persado Portal. At this phase, you’ll receive the design and copy options you aligned on with the Persado team, alongside three strategic data points to help you decide which option you’d ultimately like to proceed with:

  • Performance Prediction Scores: How well content is predicted to perform.

  • Compliance Risk Scale: A way to assess compliance risk at a glance.

  • Content Intelligence Brief: A comprehensive analysis of each Variant, down to why Persado recommends specific word choices.

This article will dive deeper into each data point and provide best practices on considering these scores as you review an analysis.

Performance Prediction scores will be shown next to each Variant in Portal for your review. To access the full Content Intelligence Brief, which contains more detailed information on both performance and compliance, click the blue ‘View Data’ button.

Performance Scoring

Performance Prediction Score

Definition

Scoring Details

A 1 (lowest) to 100 (highest) score indicating how well content is predicted to perform.

With Persado Create, we’ll only deliver content with high scores.

The higher the score, the more likely your copy is to outperform other messages in your industry. All scoring is based on Persado’s 10 years of engagement data.

How are Performance Prediction Scores Calculated?

Performance Prediction scores are calculated using Persado’s Knowledge Base, which aggregates data across multiple brands, industries, campaigns, and languages. These scores tell you how a message is predicted to perform based on the grand scheme of messages in your industry in our Knowledge Base.

We use engagement data (e.g., clicks) from your particular industry to calculate these scores. Our knowledgebase contains over 10 years of engagement data (200B interactions annually) attributed to tagged words and phrases. We measure how individual words and phrases impact performance, which enables us to predict how well any given message, composed of various words and phrases, will perform in market.

One caveat to keep in mind: The more any given word or phrase has been tested, the more certain we can be in the performance score. If your brand is using novel language, it might take some time to build up high-confidence scores.

Can I use Performance Prediction scores to compare my brand to a competitor’s?

Persado can provide a strong directional view of how your messaging is expected to perform relative to broader industry language patterns, but Performance Prediction scores are not designed to serve as a head-to-head competitive benchmark.

These scores are calculated using Persado’s Knowledge Base, which is built from industry-wide engagement data across many brands, campaigns, and languages. As a result, the score indicates how likely a given message is to perform relative to other messaging patterns we’ve observed in your particular industry overall.

The score is best used to compare message Variants within the same campaign, rather than to compare performance across different brands or campaigns, where factors like audience, offer, timing, and channel can also influence results.

Content Intelligence Briefs

We often get questions about why our AI recommends certain messages over others. Think of our Content Intelligence Briefs as the “brains” behind the operations: your one-stop shop for understanding the emotional language, narratives, positioning, and formatting elements that are woven into each Variant. We’ll also list out the compliance regulations that our system automatically checks against—this is an ever-growing list.

For more information about Persado’s ontologies, or our systematic way of tagging language, check out this comprehensive reference guide.

How is Compliance Risk Calculated?

Persado quantifies risk at three levels: low, medium, and high.

  • Observations marked with a low-level risk regard minor issues. This could be related, for instance, to the wording of a sentence for which more transparent alternatives can be picked.

  • A risk characterization of medium pertains to serious considerations regarding the alignment of the content with related regulations.

  • High-level risks highlight threats of regulation breach with severe consequences.

Persado's compliance product is powered by a sophisticated workflow leveraging an arsenal of AI models. The steps of the workflow embody optimized models tuned with expert knowledge and insights regarding regulations and their application in practice.

Best Practices for Using Scores and Briefs

Ultimately, how you use these scores is up to you! Think of each score as a different information point you can use to evaluate your content; they’re intended to meet your needs. Here are some best practices to keep in mind:

  • You don’t need to pick a Variant simply because it has the highest score: All of the Variants we’ll provide with Persado Create will be data-driven, so you can focus more on the goals you have for the particular campaign at hand. This could vary from capitalizing on top-performing emotions in your industry to trying out new language in market to see how it resonates with your audience. Share your goals with your Persado team, and we can help make recommendations for your final selection!

  • Validate scores in market and confirm what works for your audience: Ultimately, Performance Prediction scores aren’t guaranteed; higher scores mean a greater likelihood that the message will outperform other messages.

    • If you do deploy 3+ Variants in market, any metrics like clicks and orders that you can provide will inform our AIs performance over time.

  • Leverage Content Intelligence Briefs during internal review: These Briefs are designed to give insight into how Persado drafted the content for a particular campaign, and why. Check out which messaging components we’ve included, which tags are present, and how everything is tied to the original request.

Did this answer your question?