A Bayesian Approach for Flight Fare Prediction Based on Kalman Filter
Decision-making under uncertainty is one of the major issues faced by recent computer-aided solutions and applications. Bayesian prediction techniques come handy in such areas of research. In this paper, we have tried to predict flight fares using Kalman filter which is a famous Bayesian estimation technique. This approach presents an algorithm based on the linear model of the Kalman Filter. This model predicts the fare of a flight based on the input provided from an observation of previous fares. The observed data is given as input in the form of a matrix as required to the linear model, and an estimated fare for a specific upcoming flight is calculated.
KeywordsFlight fare Observation Prediction Kalman filter Linear model
- 1.Feng, Youyi, and Baichun Xiao. “A dynamic airline seat inventory control model and its optimal policy.” Operations Research 49.6 (2001): 938–949.Google Scholar
- 2.Etzioni, Oren, et al. “To buy or not to buy: mining airfare data to minimize ticket purchase price.” Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2003.Google Scholar
- 3.Rama-Murthy, Krishna. Modeling of United States Airline Fares–Using the Official Airline Guide (OAG) and Airline Origin and Destination Survey (DB1B). Diss. Virginia Tech, 2006.Google Scholar
- 4.Groves, William, and Maria Gini. “A regression model for predicting optimal purchase timing for airline tickets.” Technical report (2011).Google Scholar
- 5.Diebold, Francis X. Elements of forecasting. South-Western College Publ., 2006.Google Scholar
- 6.Maybeck, Peter S. “The Kalman filter: An introduction to concepts.” Autonomous robot vehicles. Springer New York, 1990. 194–204.Google Scholar
- 7.“QuantStart.” State Space Models and the Kalman Filter - QuantStart. N.p., n.d. Web. 10 May 2017.Google Scholar
- 8.“An Explanation of the Kalman Filter.” Mathematics Stack Exchange. N.p., n.d. Web. 10 May 2017.Google Scholar
- 9.Harrison, Jeff, and Mike West. Bayesian forecasting & dynamic models. New York: Springer, 1999.Google Scholar
- 10.“State Estimation with a Kalman Filter.” https://courses.cs.washington.edu/courses/cse466/11au/calendar/. Web. 10 May 2017.
- 11.“Linear Time-Invariant Systems.” Stanford University. N.p., n.d. Web. 10 May 2017.Google Scholar
- 12.Kosanam, Srikiran, and Daniel J. Simon. “Kalman filtering with uncertain noise covariances.” (2004): 375.)Google Scholar