The distance travelled, the time of purchase, the cost of fuel, the airports of exodus and influx, dates of commute, aviation company and the class of travel are just a few of the many factors that affect flight prices. Prediction is a well-known field of study that uses predictive modelling methods and historical flight data to make precise predictions about airline ticket pricing. Every carrier uses a unique set of rules and algorithms to calculate the right price. This paper’s goal is to analyse several hypothesis tests to increase the authenticity of the flight booking record set that was acquired from “Ease My Trip.”The record set would be skilled and a sustained target parameter would be forecasted utilizing various machine learning techniques. By choosing a particular set of factors that affect airline ticket prices, this study investigates the problem of flight pricing. The schedule, destination, length of the journey, and other events like holidays or vacations all affect how much a ticket costs. Before planning a trip, people may preserve time and money by being aware of fundamentals of airline fares. Six distinct ML models are utilized to forecast travel costs after Ease My Trip dataset is examined to provide insights into airline fares. To find the primary determinants of flight costs, the performance of different models is compared, XGBoost classifier outperform with test score of 0.95927654 and MAE of 2616.627154.