System and method for specification of a marketing mix econometric model using feedback from a digital attribution system

This disclosure provides a method including analyzing outputs from a digital attribution system, determining potential input factor attributes that are highly correlated to output dependent variables, and generating a specification for an econometric marketing mix model, the specification including the input factor attributes thus determined. The result is a marketing mix model specification that is more accurate for backcasting and forecasting than what prior approaches can produce. In some implementations, the method may be implemented using a system comprising a processor and/or one or more computer-readable storage media that stores instructions executable by the processor to perform the operations described herein.

Publication: 
Technical Disclosure Commons
Author: 
McDonough, Timothy
Document Type: 
Research
Paywall: 
Free

Leave a comment

Comment Policy
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.