Each network specific passive or active engagement is compared within our trained model, which bases its learnings on historical Organic and Paid Data to generate Beta weights (constantly updating value weights) for each data point independently on a per post basis.

Reach and impressions for non-authenticated accounts are calculated through machine learning.
Impressions and brand awareness are the most common metric used
to anchor advertising and marketing objectives. Our model backs into impressions to deliver valuation that aligns with an advertising equivalency for CPA/CPE.

Brand equities (i.e. post content data, or specific brand value factors, that appear within the body of a post that align with brand name, brand mention, tagline, keyword, or hashtag) are weighted and adjusted based on post performance, and provide an input value for the raw brand value score. They do not hold an independent numerical value.

Based on channel, placement and format, visual and audio metrics are derived via an image or video scanning process. Detections of all visually branded elements within a post are valued based on calculations of size, duration (not valid for image), location/position, and clarity (visibility and clutter).