Coca-Cola Andina Boosts Efficiency and Customer Satisfaction with Analytics on AWS

Based in Latin America, Coca-Cola Andina packages and distributes products for Coca-Cola and other brands. It oversees 10 production plants and almost 100 distribution centers across Chile, Argentina, Brazil, and Paraguay. With stock, employees, and its fleet of trucks spread internationally, Coca-Cola Andina compiles, stores, and tracks large amounts of data to keep its operations running smoothly. But using on-premises storage, the company found it difficult to keep data up to date and conveniently accessible to generate useful insights. For example, inventory and delivery analytics data were updated only once a day. The company couldn’t make accurate operations decisions based on data that was possibly already 24 hours old. Coca-Cola Andina wanted better visibility across all its facilities and processes, and that meant gathering data more frequently and making it simple to access at all levels of the organization in a user-friendly way for consumption.

Coca-Cola Andina has been using AWS since 2020, and in 2021, the company built a data lake on AWS and began migrating all its data from its on-premises storage to the cloud. The migration required a scalable solution because Coca-Cola Andina had a large amount of existing data to migrate in addition to the new data coming in daily. The company used Amazon Simple Storage Service (Amazon S3), an object storage built to retrieve nearly any amount of data from anywhere, to store the incoming data from both sources. Amazon S3 scaled seamlessly to support the storage needed.

Then, Coca-Cola Andina built its internal Thanos application to manage inventory, track operations and deliveries in near real time, and more. “We moved from no visibility to a cloud solution that gives us visibility across our operations,” says Pablo Sereno, corporate manager of internal operations digitalization at Coca-Cola Andina.

With Thanos, Coca-Cola Andina has enhanced its visibility into its operations and various processes across facilities and countries. Instead of updating once per day, Thanos updates its data every 15 minutes. “In Thanos, we have information about product distribution from the initial order to the collection of payment and the return of the delivery truck,” says Sereno. With this data on Amazon S3, Thanos presents an online dashboard that organizes Coca-Cola Andina’s operations data into accessible, digestible tables and graphs. For example, the company can view the status of each distribution center, track the names of employees and their productivity throughout the day, and combine various other metrics about processes, employees, and trucks. It can also track the status of specific orders and discover the cause of anomalies and interruptions. Thanos is also used by different applications running on the company’s environment to track orders for each client, such as its business-to-business platform, notification service, and others.

Coca-Cola Andina uses Thanos to pull data from Amazon S3 and Amazon Relational Database Service (Amazon RDS), a collection of managed services that makes it simple to set up, operate, and scale databases in the cloud. It also uses AWS Lambda, a serverless, event-driven compute service, to perform analytics and generate near-real-time insights. Coca-Cola Andina has taken advantage of this visibility to improve its operational efficiency. It has improved the fill rate of orders by 1 percent, reduced the frequency of being out of stock by 0.2 percent, and reduced the number of orders not received by 0.3 percent. Additionally, the company has been able to double the number of stock-keeping units in its portfolio, offering a broader range of product categories. As a result of these changes, its customers are much more satisfied with its service.

In addition, Coca-Cola Andina is reducing wasted delivery attempts by using AWS to run machine learning models that predict whether a customer will be available at the time of delivery. “We’re calculating the probability that an order will not be received by the customer upon arrival, and we take preventive actions,” says Sereno.