Elevating Predictions: Sculpting Flight Delay Predictions with Recursive Feature Elimination

With the rapid development of the aviation industry and the significant growth of aviation data, how to use big data technology to accurately predict flight delays has become a problem that needs to be solved in the civil aviation transportation industry, and the application of big data models in the aviation field has also become crucial. To address this challenge, a new combinatorial forecasting method is proposed in this study. This method integrates random forest algorithm and recursive feature elimination technology to construct a comprehensive prediction model, aiming at improving the accuracy and efficiency of flight delay prediction. Experiments show that the proposed method performs better in the prediction accuracy and prediction error of flight delay data after the data is normalized to eliminate the influence of different dimensions and magnitudes on the model performance, which proves the effectiveness and practicability of the proposed method.