FLIGHT TICKET PRICE PREDICTION
Mityam Kumar, Sunny Kumar Sinha, Kriti Sinha, Kunal Kumar
Abstract
This research paper presents a study on predicting flight ticket prices using machine learning techniques. The aim of this study is to develop a model that can accurately forecast the prices of airline tickets, which is crucial for both consumers and airlines. The study utilizes a dataset of historical flight prices along with relevant features such as departure date, airline, and route information. Various machine learning algorithms, including regression and time series forecasting models, are employed to train and evaluate the predictive models. The performance of the models is assessed using metrics such as root mean square error (RMSE) and mean absolute error (MAE). The results indicate that the developed models can effectively predict flight ticket prices with reasonable accuracy, providing valuable insights for travellers and airline companies.
References
[1] Li, C. W., M. M. Benjamin and G. V. Korshin. (2000) Use of UV spectroscopy to characterize the reaction between NOM and free chlorine. Environmental Science and Technology 34(12), 2570-2575. [2] Benjamin, M. M. (2002) Water Chemistry. 1st Ed. McGraw-Hill, New York, chapter 3. [3] Li, C. W., C. H. Chiu, Y. H. Lee and Y. M. Chen. (2008) Integration of ceramic membrane and compressed air-assisted solvent extraction (CAXE) for Cr(VI) recovery. Proc. of 2008 IWA North American Membrane Research Conference, Amherst, USA, 101-108. [4] Pollard, A. (1978) Flow in Tee Junction. Ph. D. Dissertation, University of London, UK. [5] Kareem, A and C. M. Cheng. (1984) Across wind response of towers and stacks of circular cross section. [6] Department of Civil Engineering, University of Houston, Report No. UHCE84-6, Houston, TX, USA. Yang, L. J. (2011) US Patent 8,033,499B2.