Flight delay model establishment method, prediction method and device

Abstract

The invention provides a flight delay model establishment method and device and a prediction method and device, and relates to the technical field of machine learning, and the method comprises the specific steps: obtaining historical data, and carrying out the data preprocessing of the historical data; constructing input characteristics of a flight delay model for the historical data after data preprocessing; wherein the input characteristics comprise non-weather characteristics of the flight and weather characteristics of the flight; performing random stratified sampling on the historical data after data preprocessing to obtain a training set, a first test set and a second test set; determining a target weather feature from the weather features of the flight based on a preset algorithm; establishing a corresponding basic model according to the non-weather characteristics of the flights of the training set and the at least one target weather characteristic; over-fitting of the basic model on the training set is prevented through expression of the basic model on the first test set; and combining the plurality of basic models into a flight delay model through the second test set. Overfitting can be prevented, and an ideal prediction effect is obtained.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a flight delay model building method, prediction method and device. Background technique [0002] Accurate prediction of flight delays in advance will help passengers choose more suitable flights according to the possibility of flight delays, and for passengers who have purchased air tickets, it will help passengers plan their time reasonably or modify their travel plans in a timely manner. [0003] Weather is the most important factor causing flight delays, accounting for about 60% of all domestic delayed flights. Severe weather can cause planes to be unable to take off and a large number of passengers to be stranded. Therefore, the prediction of flight delays only based on flight dynamics and historical data will lead to inaccurate predictions due to insufficient predictors. There are many weather reasons for flight delays, such as low visibility, low cloud base, hig...

AI Technical Summary

Problems solved by technology

Moreover, the weather will affect the normal departure plan of the flight in multiple time and space dimensions. The weather for several hours before and after the flight departure time, the weather at the airport where the flight departs and its surrounding areas, and the weather at the airport and its surrounding areas when the flight arrives may all affect to the actual departure time of the flight

Due to the large number of weather features that affect flight delays, the model that uses weather to predict flight delays is prone to overfitting and cannot obtain ideal prediction results

[0004] Aiming at the problem that the above-mentioned existing technology that uses weather to predict flight delays is prone to overfitting and cannot obtain ideal prediction results, an effective solution has not yet been proposed

Images