R/F Approach - "What Has Changed and Why it Matters" - Working

Current R/F Approach - Overview

Geopath’s existing Reach & Frequency approach was built around highly aggregated, anonymous carrier data. This mobile data was used to determine average frequency and understand general home locations, which allowed us to look at the footprint of audiences in different markets.

However, there was no device-level data available to us at the time for validation of the approach. This lead to outputs from the existing methods that were misaligned for some packages of inventory, where higher package-level Reach across the market should have been reported.

New R/F Approach - Overview

The new Reach & Frequency approach is centered around observed data. This approach utilizes machine learning, observed Reach data, and several feature inputs to train on how Reach and Frequency function over time.

This then provides us with predictors for Reach, and a model that allows us to calculate package-level Reach and Frequency for any campaign length, aligned with the observed data ±5%.