Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{170466,
        author = {Shanmugapriya and Yokeswari and Miruthula and Suganya and Kumarakrishnan},
        title = {Flight Fare Prediction using Variational Autoencoders – Generative AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {7},
        pages = {1232-1238},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=170466},
        abstract = {A flight price prediction model utilizing a Variational Autoencoder (VAE) employs generative artificial intelligence to anticipate airfare trends, thereby providing travellers with valuable insights regarding the best times to make bookings. This model is trained on historical flight data, which encompasses factors such as pricing trends, booking timings, and seasonal demand fluctuations, enabling the VAE to discern patterns across diverse market conditions. The architecture of the VAE includes an encoder that condenses flight data into a latent space, effectively capturing essential features that drive price variations, and a decoder that reconstructs this data to produce realistic price forecasts. The representation within the latent space permits the VAE to sample various potential pricing scenarios, thereby simulating future price movements. By generating a spectrum of possible prices, the model effectively addresses the uncertainty and volatility characteristic of airfare markets. This adaptive methodology allows for real-time updates, responding to new trends or abrupt changes in demand. Consequently, the model not only improves prediction accuracy but also offers timely recommendations, enabling users to secure flights at the most favourable rates. This VAE-based approach is particularly advantageous in a swiftly evolving market, assisting travellers in obtaining the best fares while adapting to real-time price changes, ultimately enhancing the affordability and accessibility of travel},
        keywords = {Variational Autoencoder (VAE), flight price prediction, price trajectories},
        month = {December},
        }