Flight Delay Prediction using GANN - An Improved Artificial Neural Network Model Integrating Genetic Algorithm

One of the difficult situations in the business world, flight planning involves a lot of unpredictability. Such a situation happens when delays happen; they have a number of root causes and cost airline companies, providers, and travelers a lot of money. Airlines, airports, and passengers all suffer considerable financial and other losses as a result of flight delays. As a result, anticipating the possibility of a delay based on the characteristics of aircraft closes a critical information gap between airlines and passengers. The prediction analysis gleaned from this research can serve as a prototype for identifying operational factors that cause delays in any situation. The flight delay analysis is based on the scheduled arrival, departure, and actual time. This study thoroughly assesses models for forecasting flight delays under this circumstance. Machine learning techniques were used in research on predicting flight delays. The best approach for anticipating flight delays has been determined by comparing the performances of various algorithms. Artificial Neural Networks (ANN), have demonstrated their high accuracy when modeling sequential data. Adam Optimization algorithm has been used to optimize the ANN algorithm. Lastly, a novel aviation delay method is optimized using an artificial neural network (ANN) in conjunction with a genetic algorithm (GA) in response to the important parameters discovered for flight delay prediction. The GANN model's performance has been confirmed, showing that it can accurately forecast delays with a score of 89%.