PREDICTION OF AIRLINE PRICES USING MACHINE LEARNING MODELS

Abstract

The aviation industry has experienced significant growth and transformation in recent years, driven by factors such as increased global connectivity, rising disposable incomes, and advancements in technology. Nowadays, airline ticket prices can vary dynamically for the same flight. From the passenger's perspective, if they want to save money, the appropriate model is required that predicts the ticket prices.

This study explores advanced machine learning techniques such as random forest, gradient boosting, and XGBoost algorithms in predicting the prices of flight tickets based on the features such as departure and arrival times, number of stops, and route specifics. The XGBoost with missing values outperforms the other models with an  value of , indicating a high accuracy in capturing the variability in prices for Indian flights. The findings highlight the potential of machine learning models to enhance pricing strategies in the aviation industry, offering significant benefits for both airlines and passengers.