Optimizing Travel Costs: A Comprehensive Machine Learning Approach to Airfare Price Prediction

  • Unique Paper ID: 166739
  • Volume: 11
  • Issue: 2
  • PageNo: 1735-1741
  • Abstract:
  • The project delves into the intricate realm of global airline pricing strategies, leveraging advanced machine learning techniques to analyze and predict airfare prices across various airlines and destinations. By scrutinizing 136,917 flight records from prominent carriers such as Aegean, Austrian, Lufthansa, and Turkish Airlines, the study elucidates the multifaceted dynamics of pricing policies in the aviation industry. Utilizing a broad spectrum of machine learning models, including AdaBoost Regression, Gradient Boosting Regression, and Convolutional Neural Networks (CNNs), the research provides comprehensive insights into the complex interplay of factors influencing airfare pricing. Despite challenges in data preprocessing, such as handling time attributes, the study showcases remarkable predictive accuracy, with certain models achieving up to 100% R2 score on specific datasets, notably the Austrian SKG-ARN route with Decision Tree Regression. These results underscore the efficacy of machine learning approaches in forecasting airfare prices, paving the way for enhanced consumer decision-making and industry optimization.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 2
  • PageNo: 1735-1741

Optimizing Travel Costs: A Comprehensive Machine Learning Approach to Airfare Price Prediction

Related Articles