HOW AMALTHEA IMPROVES CHEESE YIELD AND SUSTAINABILITY WITH ARTIFICIAL INTELLIGENCE FROM INFOR

One of the biggest challenges for dairy manufacturers is the unpredictability of the main ingredient, milk. Its composition varies between producers and seasons, which means there is no standard that can be applied to every batch of raw milk to maintain quality and profitability. To ensure the consistency of the cheese, keep customers loyal and maximize profitability, the Amalthea goat cheese producer needed an alternative to monitor and direct the entire cheese production process as quickly as possible.

Amalthea is the leading producer of goat's milk cheese in the Netherlands and sells its products in more than 35 countries. Improving milk cheese production not only increases profitability, but also improves sustainability practices, since extracting more product from raw milk reduces waste. For every 1% increase in yield, the company saves approximately 500,000 euros, which it reinvests in developing its business. It plans to significantly increase its manufacturing capacity in five years to meet the high demand for more cheese varieties and innovative products such as CleardMilk®, Whey and other components extracted from raw milk.

For each batch of cheese, Amalthea used to set a margin target based on previous production. When a batch of cheese deviated from the planned value or when it wasn't set, the plant operators were forced to take action, making changes to production to make the process more efficient. Production problems were identified by manually processing the data and analyzing it on a weekly basis. With approximately 240,000 liters of milk processed per day, it was not ideal to wait a week or sometimes a month to draw conclusions and make the necessary changes to the system to optimize it.

"We had to do the milk production calculations manually, which we could only do once a week or once a month, and that was too late. What's more, we didn't have the capacity to calculate yields per batch; we only did it at an aggregate level. But now, with Infor Coleman AI, not only can we see the yields per batch of cheese in real time, but it also gives us direct insight into what contributes to higher or lower milk production, so that operators can take direct action," explained CFO Joris Aarts.

In 2020, they modernized their ERP with Infor CloudSuite Food & Beverage and harnessed the power of the Infor OS integrated technology platform to solve a critical business problem that was difficult to resolve due to outdated and disconnected applications, data silos and a lack of time and resources. The modernization created AI-driven applications in less than 90 days. As innovation is in Amalthea's nature, it was a logical step.

By applying Infor Coleman Artificial Intelligence to orders, previous manufacturing batches and other production attributes, the Machine Learning model detects batches that deviate from the margin target, along with an explanation of the main reasons for the value obtained. It's a process that takes place on a daily basis and the information is provided through flexible interfaces depending on the end user - CloudSuite Food & Beverage homepages for operations 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. Implemented in less than 90 days, the solution supports decision-making to stabilize the process for future manufacturing orders:

  • Adjust and establish the margin objective;
  • Understand potential profitability factors and determine variations;
  • Updating the parameters of the cheese-making process.

 "What we also saw and learned is that, for some batches of cheese, we didn't have the correct target," said Aarts. "Infor Coleman AI showed us the average milk margin for all batches of cheese since they were received, and we used this information to change the target to the correct value, so that the parameters in place were aligned for the best possible result."

With Infor Coleman AI, Amalthea can now guide the cheese production process faster and with greater precision:

  • 7x faster identification (from weekly to daily) of margin deviations;
  • Recognition of the main reasons for profitability and identification of subsequent optimization actions;
  • More precise profitability objectives;
  • Stabilize process variability for margin and better quality;
  • 500,000 euros of annual savings for every 1% increase in yield;
  • Savings of 10 hours per week in data collection and analysis;
  • Greater sustainability with more profitable products and less waste;
  • More satisfied customers with the consistency of high quality cheese.

Another big win for the company is that its operators don't have to spend their time diagnosing problems due to margin deviations, since the Infor system automatically generates actionable information or explains the reasons for deviations. They can then focus their efforts on stabilizing the cheese production process and continue to grow more efficiently.

"The partnership with Infor and its data science team is excellent. They listened very carefully to our requirements and, in a very short time, provided an excellent tool. It's easy to understand and use, so we can improve our process and margin, which makes my life easier," said Liesbeth Stoopen, operations manager at Amalthea.

Infor CloudSuite Food & Beverage supports Amalthea throughout the supply chain - from milk reception to the cheese warehouse. The system interfaces with production automation in the factory, such as weighing units and processing tanks. It also makes financial close much faster than it used to be, from weeks to days. Having the business with Infor up and running in the cloud is the basis for growth, as data will play an increasingly important role in dairy production.

"Infor has a process catalog specifically designed for the dairy sector, which provides insight into the use of milk and its profitability. It's the most important factor for our cost and Infor has already helped us save money," said Aarts. "Now, with the implementation of Coleman AI, we can extend our goal even further, because we have real-time information on milk production."