Gaussian Processes for Flight Delay Prediction: Learning a Stochastic Process

What is it about?

This paper presents an efficient machine-learning approach to predict flight delays. The proposed Gaussian Process Regression (GPR) model employs the day of flight as a pivotal feature for delay forecasting. We analyze flights from various routes and gauge the efficacy of the presented learning technique by comparing the predicted delays with the actual ones. Given the inherent challenges in precisely forecasting delays, we opt to predict the delays with a 95 \% confidence interval. Also, an analysis of error propagation in relation to the forecast horizon is conducted, enabling us to determine the optimal prediction time frame. Such predictive insights hold immense potential for airlines, offering them the leverage to strategize flight operations and issue timely advisories.

Featured Image