CFO, Amalthea Group B.V
Amalthea is a goat cheese and CleardMilk producer in the Netherlands with customers in 35+ countries. We work every day to make the most of the top-quality goat milk that we get from around 50 goat farmers who are members of the Amalthea Cooperative of Goat Farmers. Our mission is to enhance the lives of consumers, customers and farmers by making delicious and nutritious dairy products in a sustainable way, based on utilizing the richness of goat and cow milk to the full extent.
Our thinking starts with consumer and customer requirements. Other important principles are sustainability and animal welfare. All three of these principles are the foundation for our vision and we aim to continue developing together with our customers in specific products, ranges, services and innovations.
A big challenge for dairy manufacturers is the unpredictability of milk. Milk composition varies across farmers and seasons, especially for goats milk, there is no standard recipe to apply across all raw milk batches to achieve consistent quality and yield. To ensure cheese consistency, keep customers loyal, and maximize yield potential, Amalthea needed a better way to monitor and steer the cheese production process as fast as possible.
Improving cheese yield from milk not only improves profits for Amalthea but also improves sustainability since extracting more product from raw milk reduces waste. For every 1% increase in yield, Amalthea saves approx. 500,000 euros that it reinvests to expand production capacity. We plan to almost double our manufacturing capacity in five yrs to meet the high demand and create innovative products such as CleardMilk®, whey and other components extracted from raw milk.
For each cheese batch, we used to set a target yield based on past knowledge of production. When a batch deviated from the target yield or the right target yield wasn’t set, factory operators had to act and make changes to production to make the process more efficient. Production issues were identified by processing data and analyzing it manually, on a weekly or monthly basis. With approximately 250,000 liters of milk processed each day, it was not optimal to wait sometimes a month to get insights and make the necessary system changes to optimize the yield.
When manually calculating milk yield at an aggregate level, there was too much delay, and we were not able to calculate the yields per batch. We could improve the milk yield somewhat but now, with the implementation of Infor Coleman AI, we see the yields per cheese batch in real-time. It also gives us direct insight into what contributors are causing a higher or lower milk yield so operators can quickly act.
This process runs daily, and insights are delivered to CloudSuite Food & Beverage Homepages for Operators and Infor Birst dashboards for management. Amalthea’s AI-driven yield deviation detection and explanation is now fully automated, from data collection to processing and presentation.
Amalthea modernized its ERP with Infor CloudSuite Food & Beverage and leveraged the power of the platform technology Infor OS with low code services, data integration, data lake, AI/ML, analytics, and more to extend the ERP to solve a critical milk yield business problem.
With Infor Coleman AI, we now steer the cheese production process faster, with more accuracy. Operators don’t have to spend time diagnosing issues with yield deviations, the system automatically generates actionable insights. Operators are happier with direct insight and can focus their time on stabilizing cheese production.
We learned that for some cheese batches, we did not have the correct target yield value. Coleman AI showed us the average milk yield of all the cheese batches since go-live, we used this information to change the target value to the correct value so that the right parameters are in place for the best results.
In the past, we could make this milk yield calculation only with hindsight. We did it once per week or month, it took more time, and more people, and the information we got was less detailed and not per individual batch. Meaning you cannot go last mile in this milk yield. Now, with newer and faster insights, we can immediately change some parameters to maximize yield.
Milk utilization is the most important driver for our cost, and Infor already helped us to save on that with a process catalog in CloudSuite Food & Beverage designed for dairy to give us insight into milk utilization and yield. With Coleman AI implemented, we can stretch that even further, we have more real-time and faster information about the milk yield. Case Study Video
The modernization formed the building blocks to create AI-driven capability in less than 90 days. The Infor partnership and data science team have been great as they really listened very carefully to our requirements, and, in a very short time, they delivered an easy-to-use tool so we can improve our process and yields.
Amalthea’s AI-driven yield deviation detection and explanation helps in decision-making to stabilize the process for future manufacturing orders by:
- Adjusting the target yield
- Understanding yield drivers and potentially fixing the input variations
- Updating the process parameters of the cheese making
Amalthea’s AI-driven yield deviation detection and explanation help steer the cheese production process faster, and with more accuracy:
- 7x faster (from weekly to daily) identification of yield deviations
- Identification of main contributors to the yield, for subsequent action to optimize yields
- More accurate target yields
- Stabilizes the variability in the process for more predictable yield and quality
- €500,000 annual savings for every 1% increase in yield
- 10 hours per week time saving in data collection and analysis
- Improved sustainability with more product yield and less waste
- Happier customers with high-quality cheese consistency
Infor CloudSuite Food & Beverage supports Amalthea across the supply chain — from milk reception to the cheese warehouse. The system interfaces with the production automation in the factory, such as weighing units and the processing tanks. We put up to 30 parameters per cheese batch into the system and applied Coleman AI to all the data collected in the data lake. The ML model detects batches that deviate from the target yield, along with the main contributors to the yield value.
What was wow for me is that Coleman AI instantly generates the main contributors to the deviation, so we do not have to figure this out and analyze the data ourselves. So this machine learning directly finds the contributors to why this milk yield is higher or lower. For example, did it cost more time? Was the temperature of the milk higher or lower than the average? Was the quality of the milk different?
What we also saw and learned is that for some cheese types, we did not have the correct target value in our systems, and that came especially in the beginning when Infor Coleman AI showed us the average milk yield of all the cheese batches since a goat’s lifespan. Now, we have changed this target value for some cheese batches. By changing the target value to the correct value, you can put your parameters for the best quality and maximum yield.
I am most proud of the real-time insights that we have per batch because it has the biggest impact on improving our business. Having insights is one thing but having them timely and embedded in our workflow so we can act is the biggest win. Our factory is at capacity, and we are doing a business case of doubling the capacity. With AI we can speed up the process of the business case because our investors see the positive results they need to invest more in Amalthea’s expansion.
About Amalthea Group B.V
Amalthea is a Dutch goat cheese and organic cow cheese producer affiliated with the goat farmers cooperative with the same name. The highest quality goat and organic cow milk is delivered every day and is then prepared in Amalthea's modern cheese factory, where it is turned into award-winning Dutch goat and organic cow cheese.