Gaussian Processes for Flight Delay Prediction: Learning a Stochastic Process

This paper presents a machine-learning approach to predict flight delays. Whereas neural networks are extensively studied for predictive capabilities, they involve nonintuitive design and extensive analysis, particularly in training and optimization processes. Instead, the proposed framework employs Gaussian processes as a supervised learning technique for flight delay prediction. This data-driven approach trains the model using prior information, specifically the mean and covariance tied to existing data. The proposed Gaussian process regression model employs the day of flight as a pivotal feature for delay forecasting. We analyze flights from various routes and gauge the accuracy of the presented learning technique by comparing the predicted delays with the actual ones. Given the inherent challenges in precisely forecasting delays, we predict the delays with a 95% confidence interval. Also, an error propagation analysis in the prediction horizon is carried out to determine the optimal time frame for prediction. The proposed method for flight delay prediction is important as airlines can strategize flight operations and issue timely advisories.