Exploratory data analysis for improved cow health and milk quality

Digitalization is rapidly advancing across all sectors, and the sources of data are continually increasing and improving. For some time now, we have been collaborating with a partner that develops and produces feed for dairy cows. Through data analysis, we have been able to prove that their feed produces more nutritious milk.

Today, the majority of milking is done with the help of milking robots. This is advantageous because it allows us to obtain detailed data on milk quality and quantity for each individual cow.

You are what you eat…

… and the same goes for cows. The amount and quality of milk are influenced by what the cow eats and how she feels.

In this project, we wanted to examine the relationship between what cows eat and what they produce. Specifically, does our customer’s feed result in more nutritious milk?

Of course, this is not only beneficial for humans who can enjoy nutritious and delicious milk, but cows that produce good milk are also happy and healthy. It’s a win-win situation for everyone!

Happy cows

Here’s how we did it

The feed producer had collected and stored a lot of data from their customers’ milking robots over the years, which they wanted to explore. They also had data on farmers who used their feed versus those who used other feeds. We asked the question:

– Is there a difference in the milk quality between farmers
who use
our customer’s feed and those who do not?

Initially, it was about creating graphs to quickly get an overview of the data. Seeing data in tabular form is one thing but visualizing it over time is another. Visualizations emphasize relationships between different data points that are difficult to discern by just looking at numbers.

To confirm that our interpretations of the data aligned with the customer’s knowledge, we discussed it together. At this stage, the customer is usually able to help us by providing insights and important details about the underlying aspects of what the data describes.

Finally, we delved into some simple modeling of the relationship between milk quality and feed. We worked closely with the customer, maintaining tight communication between the client and a local agronomist.

So, what was the result?

In this project, we investigated whether the producer’s feed creates more nutritious milk, and this turned out to be true. Despite attempts to explain this away by looking at other possible factors, such as larger and more efficient farms and machinery, we found no other explanation than the specific feed causing the more nutritious milk.

The results of the exploratory data analysis were compiled into a presentation and an article that the feed producer will publish for their customers – the dairy farmers.

Good news for the producer and great for the cows!

News. Insights. Thoughts.

Elvenite sustainability report 2023

Elvenite sustainability report 2023

Elvenite sustainability report 2023We are proud to present Elvenite's sustainability report for 2023! Throughout the year, we have focused on improving resource utilization and reducing waste in the food industry using solutions such as AI-driven seed processing and...

AI assistants at the forefront: Google’s Project Astra

AI assistants at the forefront: Google’s Project Astra

AI assistants at the forefront: Google's Project AstraGoogle's Project Astra are redefining how we interact with technology both in personal and professional contexts. These innovations are not only enhancing our interactions with AI but also deeply integrating AI...