Data Science and Business Intelligence generate relevant information from large, partly unstructured data volumes and thus make it usable. We derive recommendations and forecasts that make the company more efficient.
In small, agile teams, we work closely with our customers from the entire Fresenius Group. We advise you, analyze data and implement user-friendly software solutions, dashboards and reports. Tenacity, patience, analytical and communication skills are the qualities that a data scientist needs.
At Fresenius, the focus is on patient welfare. This is our top priority when it comes to improving our processes. Data Science and Business Intelligence make an important contribution to this: by collecting and preparing information and making it ready for analysis. We do not limit ourselves to analyzing existing data, for example, in order to identify causes of errors and correlations. Rather, we are working on identifying patterns to make predictions and optimize processes.
People with a technical background of almost any kind can find exciting and challenging topics, through which they can help drive the company forward. If you are creative, like to tackle difficult tasks and have a degree involving analysis, then we should talk. In addition, you should be able to communicate and provide advice when dealing with different specialist departments, management and IT.
We use modern tools for our work, such as:
Predictive Analytics is about predicting future maintenance needs. So that dialysis machines do not fail, for example, but rather are maintained in good time, meaning they run without faults – for the safety of our patients. To do this, we use additional sensors that provide us with data, from which we can then draw conclusions about possible faults. We prepare this information and make it ready for analysis.
Reliable forecasts are important because deviations from the calculations often lead to unnecessary costs. We support our colleagues in Controlling with the automatic forecasting of Controlling-relevant time series on the basis of statistical models. We use Machine Learning to increase the transparency of the forecasts.
"Our dialysis bag has broken, is it still sterile?" – "The dialysis machines have been outside at low temperatures, are they still fully functional?" For questions like these, we use the Complaint Classification process. Artificial intelligence separates simple cases from more complicated cases, so that patients' and customers' inquiries and complaints can be automatically forwarded to the appropriate teams for response.
When certain parameters deviate from the norm in production, it is impossible for people to understand what could be the cause when there are 200 measured values with 40,000 variables – especially since nothing has changed in the production process.
To find out what affects quality, we use Machine Learning. The result: Even in the case of fluctuations in the raw materials, the plant continues production without errors.