Novel Approach for Fare Prediction Using Machine Learning Techniques

A survey suggests that the Flight and Cab fares vary according to various factors like location, time of the day, etc. The airline companies put into effect dynamic pricing for the flight tickets. Also, it changes with the festival, holiday season and weekends. So, what’s an excellent time to buy a flight ticket? The same can be seen with cabs as well, where the fare depends upon the number of passengers, traffic, etc. The seller has information about all of the factors, but the buyers are able to access the information that is limited through which we cannot predict the tariffs. Considering the characteristics like time of departure, the number of days left for departure and time of the day, it’ll give the prime time to purchase the ticket. Likewise, the cab companies like Uber and Ola use factors like traffic in a particular location, demand and supply factors, for example when the demand for cabs is high there is a hike in prices but when the demand for cabs is not high the prices are calculated normally according to their algorithm. Availability of drivers and type of car to travel in are also crucial factors in determining the cab fares. The motive of the paper is to analyse the factors that influence the deviation within the tariffs and the way they’re associated with the change within the prices. The impetus for the research paper is to inspect the elements which have an impact on the deviations in the tariffs and how they could be related to the variation within the prices. Using this data, build an algorithm that can assist buyers to buy a ticket at an optimal time when they get the maximum benefits and minimum fares.