Flight safety is the basis for the survival and development of civil aviation transportation industry, and with the rapid development of China's civil aviation industry, the study of aircraft safety issues is becoming more and more important. Serious flight accidents can lead to great threat to life as well as economic loss, so this paper focuses on flight safety issues, and analyzes and investigates flight key parameters segment data, aircraft overruns, and flight parameters data. In this paper, based on the relevant data from QAR , t-test was performed on the processed data through data analysis and data cleaning to ensure the reliability of the data. And the principal component components of the key data were extracted using the random forest algorithm, and the 6-bit eigenvalues were selected as the key parameters, which had the greatest influence on the landing G value of the aircraft. Then, the data set was divided according to the ratio of 8:2, and the pilot qualification was used as the label value, and the machine learning classification prediction was performed by the gradient boosting tree GBDT algorithm to obtain the pilot qualification prediction model, and the highest accuracy reached 76.3% in the test set. This paper also compares the extreme gradient boosting XGBoost algorithm, with the highest current parameter reaching 73.4%. In this paper, the gradient boosting tree GBDT is chosen to construct a flight crew qualification assessment model.