Flight delay prediction method based on big data mining processing analysis

• Main Authors: SONG WENXIAN, ZHONG DANYANG, ZHANG JIANXIANG
• Format: Patent
• Language: Chinese; English
• Published: 11.02.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a flight delay prediction method based on big data mining processing analysis. The method comprises the following steps of A, data preprocessing, collecting multi-dimensional original data, B, constructing feature engineering data in combination with preliminary feature variables and obtaining importance weights of features by adopting a random forest so as to obtain a feature set, C, matching an optimized model parameter combination based on different airport data through a mode of combining multiple grid searches with K-fold verification; and D, inputting a to-be-predicted sample into the final flight delay prediction model and obtaining flight delay data. According to the method, multi-dimensional original data are comprehensively collected, a feature combination with a large importance weight is selected, the optimal model parameter combination is adapted based on different airport data through a mode of combining multiple grid search with K-fold verification, and a prediction mode