Study on the factors affecting flight training for trainee pilots

In the field of aviation，the flight skills of trainee pilots are directly related to aviation safety and operational efficiency. Based on the training data of flight trainees from a branch of Civil Aviation Flight University of China，the Pearson correlation coefficient is introduced to evaluate the strength of the relationship between features and target variable. Based on the correlation coefficients，the key factors influencing flight training are identified， and a novel decision tree model based on Pearson correlation coefficients is established. By optimizing the model with various thresholds and tree depths，its performance in accuracy，precision，recall，and F1 score is optimized. The performance of the new model is compared with random forest，multilayer perception（MLP），logistic regression，decision tree and enhanced gradient boosting decision tree model. The results show that the new model is of superior performance，and can provide the effective guidance for flight training，and offer the theoretical support for the evaluation of flight training.