Preventing occupational accidents before they happen is one of the key tasks of statutory accident insurance. An important component in achieving this goal is advising and supervising member companies through direct personal contact. With the help of artificial intelligence (AI), it is possible to identify at an early stage those companies with an increased probability of an accident occurring in the future. This can improve the effectiveness of advice and supervision and reduce the occurrence of accidents.
Within the framework of a proof of concept, it has already been shown that a risk-based selection of companies with the aim of onsite consulting reduces the occurrence of accidents by approximately 15 per cent. This involves an AI-supported forecast of the accident trend for each company. The results of the AI thereby serve as a supporting feature in the inspection selection for the field service. Standard software and a Phyton pipeline are used. The AI models were developed by the German Social Accident Insurance Institution for the energy, textile, electrical and media products sectors (Berufsgenossenschaft Energie Textil Elektro Medienerzeugnisse – BG ETEM) together with an external partner.