Predicting safety attitudes in aviation maintenance using machine learning: An exploratory study

• The study explores the application of machine learning in predicting safety attitudes among aviation maintenance personnel. • The Random Forest algorithm was utilised to identify relationships between personality traits and safety attitudes and make predictions. • Extraversion may have the most positive influence, followed closely by openness. Neuroticism can have the most negative influence. • The total years of experience, followed by years of experience in the current role, were influencing. • Combining personality traits with demographic information can improve safety attitude predictions. This study explores the application of machine learning techniques in predicting safety attitudes among aviation maintenance personnel. Personality traits and demographic information are used for this purpose, with data obtained from an online dataset. The Random Forest machine learning algorithm was utilised to identify the relationships and to enable predictions. The obtained results indicated that extraversion had the most positive influence, followed closely by openness. On the other hand, neuroticism had the most negative impact. Total years of experience and experience in the current role are, on the other hand, the most influential demographic information. Combining personality traits with demographic information can improve safety attitude predictions. Nevertheless, definitive causal inferences cannot be established, as further analysis is required to verify the suitability of the Random Forest algorithm relative to other machine learning algorithms.