An airfare prediction model for developing markets

Air passengers (the buyers) are often looking for the best time period to purchase airfares to get as much saving as possible while airlines (the sellers) always try to maximize their revenues by revising different prices for the same service. The sellers have all the necessary information (for example historical sale, market demand, customer profile, and behavior) to make the decision whether to increase or decrease airfares at different times prior to the departure dates. On the other hand, the buyers are only able to access limited information to assist their decision making on whether to wait or purchase airfare right away. In this paper, we propose a new model that can help the buyer to predict the price trends without official information from the airlines. Our findings demonstrated that the proposed model can predict the trends as well as actual airfare's changes up to the departure dates using public airfare data available online despite the missing of many key features like the number of unsold seats on flights. We also identified the features that have the strongest impacts on the airfare changes.