The Problem: The ‘Pick’ or ‘No Pick’ Dilemma
As the biggest beverage company in the world, Coca-Cola Bottling has a major presence in Canada with 25 different brands, over 50 production facilities and more than 5,700 staff servicing 38 million customers. Their most popular brands include Coca-Cola, Minute Maid, Dasani and Powerade — household names that virtually all Canadians recognize.
Vending machines are important outlets for the distribution of Coke products. While they only represent 1% of Coke’s total revenue, it’s also the most profitable business unit and one of the few channels where the organization has full control of. As such, a crucial question is: How can Coca-Cola Canada Bottling improve customer service by identifying ideal locations for placing vending machines?
The Solution: Mobility Data
Coca-Cola underwent a thorough vetting process to ensure that the Synthetic Society by Arima datasets could help them achieve their goals — understanding how consumers move around locations and creating accurate profiles of these consumers.
Before the project commenced, they had three key expectations:
- Granularity of Mobility Data
Mobility data needed to have sufficient geographical and time granularity. In other words, it had to identify who had been physically near a vending machine and confirm they were an actual customer — not just someone who walked by. - Integration with Synthetic Society
Mobility data had to be compatible with the Synthetic Society, enabling Coca-Cola to generate detailed consumer profiles for each vending machine visit. - Statistical Significance
The sample size of both datasets needed to be large enough to yield statistically significant insights.
The Synthetic Society dataset is incredibly rich, containing more than 25,000 variables about Canadians. This gave Coca-Cola Canada Bottling the flexibility to select the most relevant attributes for analyzing their potential customers. The analysis began with 24 demographic variables, with a clear plan to expand the number of features in future studies.
What truly set Arima apart for Coca-Cola Canada Bottling’s team was the seamless collaboration.
“We always know there’s someone at Arima who can answer our questions, help us work through issues, and be receptive to our feedback. This really feels like a partnership; Arima offers a level of service you don’t get with other vendors.”
Nikita Medvedev, Director of Advanced Analytics at Coca-Cola
The Result
Arima collaborated with Coca-Cola’s Enterprise Analytics team to develop predictive models using their first-party data (e.g., vending machine locations, machine types, and revenue) alongside the Synthetic Society by Arima dataset.
Key Data Points
- 5,000+ Variables
- 25 Surveys & Panels
- 38 Million Canadians
- 850,000+ Postal Codes
An Overview of the Synthetic Society
Through extensive brainstorming sessions and technical iterations, the team achieved the following results:
- The probability of selecting a high-performing location increased from 45% to 68%
- On average, a model-selected location generated 43% more sales
- Locations chosen by the model had a 76% higher sales index compared to those selected without it
Coca-Cola Canada Bottling used the more accurate consumer and mobility data to drive efficient placement of vending machines, which in turn, led to higher revenue from relocating existing placements and adding new vending machines.
Seeing is Believing
Want to optimize your locations and drive better business outcomes? Book a demo with Arima today to see how our Synthetic Society dataset and predictive modeling can help you make data-driven decisions with confidence.
