The Integration of Machine Learning Technique with the Existing System to Predict the Flight Prices

Abstract

The cost of airline tickets fluctuates depending on a number of variables, together with the scheduling, destination, and length of the flight. By using machine learning algorithms to the gathered ancient flight data, the suggested scheme will generate a prediction model. It might be difficult for consumers to decide when is the best time to buy plane tickets, mostly because they lack the knowledge necessary to make predictions regarding price changes. In this project, our main goals were to identify underlying trends in travel costs in India byancient data and to recommend the most advantageous time to purchase a ticket.A comparative study of several methods in determining the ideal time to purchase anaircraft ticket and the expanse that may be saved if completed so is conducted as part of the research in order to validate or refute common misconceptions about the airline business. Surprisingly, the route, month, day (holiday or working day), time, commercial airlinetransporter, and day of departure all have a significant impact on price trends. While prices on some highly competitive routes, such as those between metropolitan to metropolitan cities like Mumbai and Delhi, increased in a non-decreasing tendency as the number of days until departure reduced, other paths, such as those between metropolitan and non-metropolitan cities like Delhi and Guwahati, had a set period of time during which fares are at their lowermost.According to the availability of previous data aircraft carriers operating in India are divided into two fundamental groups namely the opulent and economical group. Majority of times, the trip with the lowest fare belonged to the economical group. The statistics also confirmed that there are times of the day when prices are predicted to be at their highest. To significantly reduce the cost of purchasing flights across the Indian domestic airline market, the project's scope might be greatly expanded across the numerous routes.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 20 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.