Flight ticket fare is the most fluctuating data which varies every day. Depending on various factors that affect it directly or indirectly, we cannot say that price of the ticket stays the same or not. It is quite a tough task to predict the flight ticket fare. It may change throughout the week, month or sometimes days, but it can be predicted nearly accurate to actual flight ticket fare. The prime objective of our project “Flight fare prediction system” is to make a prediction of the flight ticket fare for the future flights. We build a machine learning model using a dataset of aircraft ticket prices for different carriers and different routes at different times of the year. The regression model which we have selected for our prediction is “Extreme Gradient Boosting”.