Machine Learning-based Flight Fare Prediction in the Indian Market

With the rising popularity of air travel in India, ac- curately predicting flight ticket prices becomes crucial for budget- con-scious travelers. Airlines employ complex pricing strategies, making it challenging for passengers to find the optimal time to purchase tickets. This paper proposes a machine learning- based model to predict flight fares in the Indian market. The model leverages a dataset of domestic and international flights in 2019 to identify key factors that influence ticket prices. We employ exploratory data analysis (EDA) techniques for data cleaning, feature engineering, and handling categorical variables. The Random Forest algorithm is then used for price prediction, with hyperparameter tuning to optimize performance. This research contributes to the development of a user-friendly system that empowers travelers to make informed decisions regarding flight purchases. Develop a model that can accurately forecast the price of a future flight ticket based on historical data and recurrent factors. By leveraging machine learning, particularly Ran-dom Forest regression with hyperparameter tuning, researchers can develop effective flight fare prediction models. This encourages travelers to make informed booking decisions and assists the aviation industry in optimizing pricing strategies.