Here is an interesting site that I came across today. The name of it is FareCast and it uses an algorithm to predict the future prices of airline tickets to the destination where you want to go so you know whether it makes more sense to purchase them now or to wait to buy them. From their site:

We use data-mining algorithms to search for patterns, in the accumulated airfare data, which are associated with significant price changes. These patterns are represented and stored in models, and the models are then rigorously trained. Once created and trained, we use these models to predict the future. Then, new, current airfares can be scored by the model to answer the question, “is the price going up or down in the future?”

Inside a computer program, simulated passengers buy real airplane tickets represented in the vast amount of data we collect every day. We build models for each day the simulated passengers are interested in purchasing tickets. Each simulated passenger receives a recommendation for the day and market they are shopping. Because our pricing data comes after the simulated shopping day, we can tell if we made the right or wrong recommendation. We tally up the results of the outcomes of recommendations made to thousands of simulated passengers. This data tells us how accurate we are. Although the simulations do not mimic real life exactly, they provide a close enough approximation for us to know the technology is useful.

Those traveling can currently use the farecast system between 55 domestic cities. It doesn’t seem that Southwest airlines is included in their system, so the comparison of low fares is missing this key low fare provider. Still, it’s an interesting idea.

I tried the system just to experiment and input a ticket from San Jose CA leaving 10/10 to Seattle and returning 10/17. The system gave me a prediction that the airfare would hold steady over the next 7 days with a 60% confidence rating and a tip to buy the ticket now.

I think the next time I’m ready to purchase a ticket I’ll be heading over to the site. Although it obviously isn’t a foolproof system, I sure would like to know if the past predicts that my ticket will be lower or higher if I wait a bit to purchase it…