This research paper investigates the prediction of airline ticket prices using various machine learning techniques. Utilizing a dataset of 10,683 records from domestic and international flights in India from 2019, we embark on a comprehensive analysis to develop a reliable predictive model. The procedure starts with meticulous data preparation to eliminate mistakes and zero values. Next, categorical data is processed using one-hot and label encoding, and Exploratory Data Analysis (EDA) is used to create specific characteristics. Employing feature selection and hyperparameter optimization, we attain notable enhancements in prediction performance and model correctness. To strengthen the model's resistance to uncertainties, we also look at how fuzzy logic might manage uncertainty in aircraft fee forecasting. Various approaches to aircraft price forecasting are shown by a thorough examination of the literature, underscoring the significance of machine learning techniques in this sector. To improve pattern detection, our suggested system combines data visualization methods like heat maps and scatter plots with forests and random tree regression. You can get precise estimates of airline ticket costs with random forest regression. Future research will concentrate on expanding the data set to include more data items to improve the model’s accuracy. With the aid of this poll, travelers should be better equipped to understand current pricing trends, make more informed decisions, and pursue easy and affordable air travel.