Flight Delay Prediction Based On Aviation Big Data And Machine Learning

Abstract

Among the many difficult scenarios in the business world is flight planning, which must account for a wide range of uncertainties. This situation in delay incidence results from a number of causes and places significant financial burdens on airlines, operators, and passengers. Airport infrastructure, luggage handling, and mechanical equipment, as well as the cumulative delays from prior flights, may all contribute to departure delays, along with severe weather, peak travel times, airline rules, and technical issues. In This Aviation Data-driven algorithm forecasts potential aircraft delays. The system takes into account a number of factors. This system employs the algorithms Random Forest (RF), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM).