This paper investigates the problem of flight price prediction. The prediction of flight prices poses a challenge for both passengers, who seek to pay a fair price, and airlines, which aim to optimize their revenues. Traditional prediction methods often fail to account for variable factors such as seasonal fluctuations, demand, and seat availability, resulting in inaccurate pricing. Therefore, developing a machine learning-based model is essential for achieving greater transparency and efficiency in the flight ticket market. The methodology employed includes the use of the following machine learning algorithms: Random Forest, Decision Tree, and XGBoost. The model evaluation was performed using an 8:2 train-test data split. Based on the performance evaluation using the RMSE (Root Mean Squared Error) metric, Random Forest proved to be the best model for flight price prediction..