Planning the production of allergy medicines using krati

The production of allergy medicines is seasonal, as it depends on several factors such as the type of pollen, weather conditions and stocks. In the case of the drug discussed in the project, it is a drug that cannot be stored in larger quantities and for a longer period of time, as the shelf life and price of the drug do not allow it. Therefore, it is important to plan exactly when and how much this medicine should be produced.

A crate-based solution

A solution based on machine learning was used in the realization of the project, the input of which was data on the amount of pollen, type of pollen, weather, drug stocks, production and sales data.

The result


During the pilot project, it was possible to achieve an accuracy of up to 91%, but the potential accuracy of 83-85% is estimated when the system is widely adopted. Thanks to the good results, the company can improve its efficiency and build additional products that offer added value when the solution is introduced.


The company implementing the project, Sifr, is a subsidiary of a Swedish company that offers various developments of artificial intelligence solutions. The company's main customers are companies from the German pharmaceutical sector, the Baltic telecom, financial and insurance sectors.