A Data-Mining Approach to Travel Price Forecasting

With the advent of yield management in the air travel industry, a large body of data-mining techniques have been developed over the last two decades for the purpose of increasing profitability of airline companies. The mathematical optimization strategies put in place resulted in price discrimination, similar seats in a same flight being often bought at different prices, depending on the time of the transaction, the provider, etc. It is the goal of this paper to consider the design of decision-making tools in the context of varying travel prices from the customer's perspective. Based on vast streams of heterogeneous historical data collected through the internet, we describe here two approaches to forecasting travel price changes at a given horizon, taking as input variables a list of descriptive characteristics of the flight, together with possible features of the past evolution of the related price series. Though heterogeneous in many respects ( e.g. sampling, scale), the collection of historical prices series is here represented in a unified manner, by marked point processes (MPP). State-of-the-art supervised learning algorithms, possibly combined with a preliminary clustering stage, grouping flights whose related price series exhibit similar behavior, can be next used in order to help the customer to decide when to purchase her/his ticket.