Flight Price Prediction for Enhanced Recommendations via Machine Learning Web Application

Airline fares are subject to fluctuations based on a range of factors, including flight schedules, destinations, and seasonal trends. The ticket prices are subject to change seasonally. The price of an airline ticket is determined by numerous factors. The advent of flight price prediction using machine learning, aided clients in purchasing the most convenient and reasonable air ticket. In this proposed research, the main goal is to build a reliable machine-learning model that can estimate flight costs and then utilize Flask to deliver it as an approachable online application. A thorough assessment of six distinct machine learning algorithms is carried out to guarantee the correctness and dependability of the model. Performance measures including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2) score were initially employed for comparison. The random forest regressor performed better than all the other algorithms examined, with the best R2 score. Feature engineering in ML model transformed raw data into meaningful features that enhanced model accuracy and predictive power. As a result, the random forest regressor is chosen to deploy in the online web application for predicting flight prices [1].