A CLOUD-BASED AUTOMATED SYSTEM FOR ANALYZING REALTIME AIRLINE PRICE TRENDS USING AI-POWERED PREDICTIVE MODELS

Kavala Bhaskara Durga; Dr. B. Sujatha

doi:10.62643/ijerst.2026.v22.n1.pp909-916

Authors

Kavala Bhaskara Durga Author
Dr. B. Sujatha Author

DOI:

https://doi.org/10.62643/ijerst.2026.v22.n1.pp909-916

Keywords:

airline fare forecasting, flight price analytics, intelligent prediction models, neural network-based time series modelling, LSTM networks, generative artificial intelligence, real-time data integration, ensemble classification techniques, web-enabled forecasting framework, API-driven prediction system. that conditional generative models are more accurate when working with structured data.

Abstract

The aviation industry has been struggling to have flight fares forecasted fast and precisely as the industry evolves dynamically. Factors such as the changes in demand, fuel costs and route specifications influence prices. The new approach presented in this research involves an attempt to resolve this issue with the help of generative artificial intelligence (GAI) to predict airfares on the fly. It provides a different model incorporating generative models, deep learning, and historical prices so that future fare predictions become more accurate. The study applies a GAI within the context of a modern web engineering system. The aim of its primary objective is to derive knowledge based on the intricate imagery and connections of the history of airline data. Using this approach, the model will be able to identify the complex relationships and be flexible to dynamism in the market. It is based on deep neural networks to deal with a wide range of circumstances and extract valuable information to get a better understanding of the numerous variables that influence the cost of flights. The strategy is aimed at predicting future events with accuracy in real time and allowing prompt reaction to the market volatility and delivering value.