Ebiquity's Mixed Marketing Modeling

of two

Ebiquity's Mixed Marketing Modeling

Seven media coverage publications or media mentions focused on Ebiquity's Marketing Mix Modeling (MMM) that were published in the last two years have been identified, four from 2017 and three from 2018. The publications covered topics such as partnership deals and evaluation of project results. Complete details of the findings from the research are below.


Six Steps to Building an Effective Data Strategy
  • Publisher: WARC
  • Date of Publication: October 20, 2017.
  • Brief summary: This report discusses the step-wise approach given by Verity Gill, a digital director at Ebiquity. One of the steps discussed by Gill is MMM.

Auditor Presses Media Agencies with New Service Under Pressure

Why Digital Advertising and If So, How?

Ebiquity Joins Facebook’s Marketing Mix Modeling Program
  • Publisher: Adhugger
  • Date of Publication: June 29, 2017.
  • Brief summary: This report gives an overview of Ebiquity joining Facebook MMM program. The deal gives Ebiquity’s customers all over the ability to leverage marketing effectiveness studies in the future.


Marketers Still Not Optimising Spend Accordingly
  • Publisher: AdNews
  • Date of Publication: July 4, 2018.
  • Brief summary: The publication discusses the result of Ebiquity’s study on how finance, automotive, Fast-moving Consumer Goods (FMCG), and E-commerce players can increase the return on their media investment by over $1 billion.

Ebiquity Strengthens its Board in AdTech
  • Publisher: Offremedia
  • Date of Publication: March 13, 2018.
  • Brief summary: This report gives an overview of Ebiquity’s hires at the launch of its EbiquityTech practice in Europe. The company hired Caroline Kan, a former member of Kellogg Europe, to launch it MMM in France.

Snapchat Provides UK Marketers with New Tools
  • Publisher: MobileMarketing
  • Date of Publication: June 13, 2018.
  • Brief summary: This publication gives an overview of Snapchat’s partnership with Ebiquity, as part of its development of the MMM partner program in Europe, to give brands the ability to measure the impact of their Snapchat campaigns, as well as on other marketing channels.


To fulfill this request, your research team searched for media mentions and coverage on Ebiquity relating to Marketing Mix Modeling (MMM), from January 1, 2017, until the present. We achieved this by consulting news mentions, industry analysis publications, reviews and evaluation articles, marketing journals and publications, academic media, and other credible media releases. In compiling the results presented in this research, redundant mentions were disregarded. For example, Snapchat’s partnership with Ebiquity, which is reported above, was also reported by The Drum. Throughout the research, no media coverage or media mention published in 2019 could be found.

of two

Ebiquity's Mixed Marketing Modeling 2

A Mixed Marketing Model is a strategy that quantifies various marketing variables and their impact on sales and market share.

How it Works

Importance of MMM Formulas and Methods in Achieving ROI Accuracy

  • ROI is a statistical tool that identifies the amount of return accrued from an investment decision. ROI is calculated by dividing the benefit from an investment by the cost incurred and expressing the value as a percentage. The formula is ROI = (Net Profit / Cost of Investment) x 100.
  • Both linear and multi-linear regressions are commonly used to determine ROI.
  • Linear regression is used when the relationship between the dependent variable and the independent variable is assumed to be continuous. This analysis takes into account factors such as predicted changes in trends and the possible impact the change could have on ROI. As a result, linear regression improves accuracy of ROI when this forecast change is considered.
  • Multi-linear regression uses several explanatory variables to determine the outcome of a particular response variable. Multi-linear regression takes into account several factors that impact ROI instead of focusing just on one, thereby improving the efficiency of the linear regression. Some factors that could potentially impact ROI are time, economic trends, industry change, and new experiments.
  • Outliers could also affect ROI of a company. Outliers result from seasonal change or random events. One method of mitigating this challenge is to identify the outlier and including only the accurate variables in a regression model. The results should explain the reason for the outlier.
  • Missing values are also potential factors that could affect the observed ROI. Missing values arise from non-availability of data or non-occurrence of events. This problem of missing values can be mitigated through various techniques including imputation, forecasting or deletion. These techniques will help deal with possible biases in variables thus increasing the efficiency of the ROI.