Optimizing L'Oréal Ads with Neuromarketing and Predictive Analytics

Utilized advanced marketing analytics techniques to improve L'Oréal's ad effectiveness by increasing brand and pictorial fixation rates, resulting in a predicted increase in brand recall accuracy from 18.18% to 77.54%.

This project focused on optimizing L'Oréal's magazine advertisements to enhance consumer engagement and brand recall. Our team analyzed eye-tracking data from an experiment involving 88 participants who read through a Cosmopolitan magazine while their eye movements were tracked. Key data points included brand and pictorial fixations and brand recall accuracy.

Using SAS, we developed three Generalized Linear Models (GLMs) to examine the relationship between ad characteristics and fixation counts. The Poisson Regression Model analyzed brand and pictorial fixation counts, while the Binomial Logit Model evaluated brand recall accuracy. Key independent variables included ad page number, page position (right vs. left), and the surface size of brand and pictorial elements.

Skills and Tools Utilized:

Software: SAS, Excel
Techniques: Poisson Regression, Logit Modeling, Dummy Variable Creation, Predictive Analytics
Analytical Skills: Statistical modeling, data interpretation, hypothesis testing, marketing strategy optimization

Power in Numbers

Stores Analyzed

Optimal Price($)

% sales drop for a $1 price increase without promotions