Airline Ticket Price Prediction using Wavelet Enhanced Hybrid Forecasting Model Approach

The exponential growth of air travel has increased the demand for accurate airline ticket price and demand forecasting systems. This research presents a hybrid machine learning model combining wavelet decomposition with extreme gradient boosting (XGBoost) to predict airline ticket prices for both Economy and Business classes. The model pre-processes and decomposes historical ticket pricing data to capture nonlinear and high frequency trends, enabling better generalization and prediction accuracy. Furthermore, the integration of Monte Carlo simulation (MCS) introduces uncertainty modelling, allowing the system to forecast not only point estimates but also probabilistic ranges. The approach addresses real-world challenges such as market volatility, seasonal demand shifts, and class-specific pricing patterns. The proposed model is evaluated using standard metrics like Root mean square error (RMSE), mean absolute error (MAE), and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, and results indicate a significant performance improvement over baseline models. Visualizations including prediction intervals, histograms, and actual vs predicted graphs substantiate the model’s effectiveness.