Gatorade Zero Revamp

A mock project on consumer insights and taste test analysis

Disclaimer:

This is purely an exercise to showcase skills. This is not a real project occurring at Gatorade. There was not a real taste test performed. While the analysis is real, all consumer data is AI-generated.

Above is a presentation for a mock project. Below are the steps I took to reach my conclusion.

Test Design:

I purchased and tasted the current Gatorade Zero Orange. I created a list of sensory attributes present in the product. Click here to see the created questionnaire.

Data Collection:

Without the resources to truly run an 80 person consumer test, I turned to AI. I provided my questionnaire to ChatGPT and asked it to simulate a study with 80 participants. This CSV file was the output.

Data Analysis:

I used Python to run statistical analyses on my dataset. From simple calculations such as Liking score means and JAR percentages, I created my tables. I then ran more advanced statistical tests, namely paired t-tests, Wilcoxon signed-rank tests, and an OLS regression model, to determine if there were significant differences between the original product and the new formulation.

You can see my code here.

High Level Conclusion:

While there was no significant difference in Overall Liking between the original and new formulations, low sweetness levels negatively affected consumer liking of the new formulation.