A Holistic Approach on Airfare Price Prediction Using Machine Learning Techniques

Globalization of markets involves new strategies and price policies from professionals that contribute to global competitiveness. Airline companies are changing tickets’ prices very often considering a variety factors based on their proprietary rules algorithms searching for the most suitable policy. Recently, Artificial Intelligence (AI) models exploited latter task, due compactness, fast adaptability, many potentials in data generalization. This paper represents an analysis airfare prediction towards finding similarities pricing different by using AI Techniques. More specifically, set effective features is extracted 136.917 flights Aegean, Turkish, Austrian Lufthansa Airlines six popular international destinations. The then used conduct holistic perspective end user who seeks affordable ticket cost, destination-based evaluation including all airlines, airline-based For cause, three domains total 16 model architectures considered resolve problem: Machine Learning (ML) with eight state-of-the-art models, Deep (DL) CNN Quantum (QML) two models. Experimental results reveal at least each domain, ML, DL, QML, able achieve accuracies between 89% 99% this regression problem, destinations airline companies.