Apriori algorithm-based analysis of causal factors of ground-floor economic catering accidents

In the post-pandemic era, as the economy recovers, the development and management of the street vendor's stall economy has become a focus of research. The aim of this study is to analyze the causative factors and their associated characteristics of street vendor's stall economy catering accidents in order to improve accident prevention. We employed a hierarchical analysis and categorized accident factors into four layers: human factors, equipment, environment and management. The causal factors were also captured by writing a Python program to capture the causal factors of the investigation reports of food and beverage accidents in the street vendor's stall economy category during a certain period of time in the recent past, and a total of 226 causal factors were extracted. On this basis, we applied Boolean-based Apriori algorithm for association rule mining and found 133 association rules. The key factors, key causal associations, and accident causation patterns were revealed by analyzing features with high support and high confidence. These findings help to improve accident prevention and safety management in the street vendor's stall economy. This study provides important insights into the deeper understanding of the groundhog economic accidents and provides substantial support for decision making in related fields.