Download PDF
C5i > Case Studies > Attitude and usage segmentation on fast food consumption
C5i Logo

Attitude and usage segmentation on fast food consumption

Technology Category
  • Analytics & Modeling - Predictive Analytics
Applicable Industries
  • Food & Beverage
Applicable Functions
  • Sales & Marketing
Use Cases
  • Predictive Replenishment
Services
  • Data Science Services
The Challenge
The client, a leading fast food restaurant chain, had been experiencing a decline in sales in few US metropolitan areas over a period of time and was interested in understanding these markets more thoroughly. They wanted to quantify the target opportunity through an attitudinal lens, and profile customers by their fast food consumption behavior. The attitude/ lifestyle-based segments also needed to cross over with client ready behavioral segments in order to develop specific offerings keeping past usage/behaviors in mind. They were also interested in targeting “value” segments more strategically so they were looking to build a predictive model to classify prospect customers into attitudinal segments.
About The Customer
The customer is a leading fast food restaurant chain operating in the United States. They are part of the consumer goods and services industry, specifically in the food and beverage sector. The client has been experiencing a decline in sales in certain metropolitan areas over a period of time. They are interested in understanding these markets more thoroughly and are looking to quantify the target opportunity through an attitudinal lens. They aim to profile customers by their fast food consumption behavior and develop specific offerings keeping past usage/behaviors in mind.
The Solution
Blueocean Market Intelligence was asked to conduct a segmentation analysis and predictive model to enable a better understanding of customer attitude and usage, with respect to fast food. They ran the segmentation using several approaches such as agglomerative, divisive, pattern detection etc. and then the results were cross-compared. The common emerging segments were further investigated for validity and mathematical properties. The segments derived were used as target variables and a mathematical model was developed using discriminant analysis model to predict segment classification based on usage, behavioral and demographic variables.
Operational Impact
  • Customized offerings based on segmentation
  • Proactive customer targeting
  • The segments such as “healthy obsessed,” “food advocates” became primary segments for targeting and messaging
Quantitative Benefit
  • The predictive model was able to predict 95% correctly on test and training datasets

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.