Comparison of Air Fare Prediction Using Various Machine Learning Techniques

Due to a rise in air service links globally, air travel is now a popular, significant, and faster form of transportation. Airline rates are thought to be impacted by several factors and are subject to frequent fluctuation, making estimation of these rates a challenging but essential task. The airline uses a pricing structure for the plane ticket. The cost of airline tickets varies based on the time of day, according to the survey. Even the weekends, the tourist season, and the pageant season have an impact on this. An aircraft ticket's price is influenced by several different elements. The buyer only has access to a limited amount of information, which is truly insufficient to estimate flight pricing, but the seller is aware of all the requirements. In this study, we use machine learning regression approaches such as K Nearest Neighbourhood, Decision Tree, and Random Forest to estimate flight fares based on basic data including source, destination, departure time and date, arrival timings, halts, and airline type. The results of the investigation show that the Random Forest Regression Model yields extremely optimal results.