FLIGHT TICKET PRICE PREDICTOR USING MACHINE LEARNING

Flight ticket prices vary significantly depending on factors such as airline, source and destination, departure date, journey duration, number of stops, departure time, and the number of days remaining before the journey. Due to these variations, passengers may find it difficult to determine the appropriate time to purchase flight tickets at a lower price. The Flight Ticket Price Predictor is a machine-learning-based system designed to predict the approximate price of a flight using historical flight-ticket data. The system collects important flight-related attributes, preprocesses the dataset, performs feature transformation, and trains a machine-learning regression model to learn the relationship between flight characteristics and ticket prices. The proposed system can use algorithms such as Linear Regression, Decision Tree Regression, Random Forest Regression, Gradient Boosting, or other suitable regression techniques. The trained model receives flight details from the user and predicts the expected ticket price. The system can provide a simple user interface where users enter the airline, source, destination, journey date, departure time, arrival time, duration, and number of stops. The prediction model processes these features and generates an estimated ticket price. Performance can be evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R² score. The proposed system therefore combines machine learning, data preprocessing, feature engineering, and regression techniques to develop an automated flight ticket price prediction system.