Overbooking, Revenue Management, and Data Mining

by Mike Trick on November 7th, 2010

Fellow blogger Guillaume Roels wrote that the hotel he reserved overbooked, so he has been exiled to a remote location and he bemoaned the lack of customer service in this transaction.  Something similar was obviously going on in my hotel, the Hilton (the main hotel for the conference).  Throughout the checkin yesterday, the desk clerks were looking for volunteers to be exiled, offering various incentives (”Free transportation! A drink vouncher! Big, big discounts, just for you!”) for people to move.  They weren’t getting any takers while I was there, so I fear the late check-ins were similarly sent off to the boondocks.

I bet the hotels got into a mess because they misestimated the number of people who showed up (or overestimated the “melt”: people who canceled in the final week or two).  If they simply took an average “no show” or “cancel in the last week” rate, I bet conference participants do so at a much lower rate.  After all, the vast majority of us have preregistered for the conference, so late cancellation means forfeiting some or all of the conference registration fee.  We have great incentives to figure out early whether we are going to be here or not.  And, perhaps people in OR or other analytic fields tend to not cancel or cancel earlier due to the organized, steel-trap-like minds we all have!  We know what we are doing, so we don’t cancel in the last week.

Of course, whether or not that is true is an empirical question, and one that can be best answered by data mining methods.  Over the course of drinks last night, a senior researcher for a large business analytics firm pointed out the disconnect we have in our field between data mining and optimization.  Often (though not always), these are seem as two phases of the “operations research process”.  Instead, there is a need for much better integration between these approaches.  Data mining should be constantly in use predicting cancellations and melt, driving the revenue management optimization approaches.

For those who were bumped by the hotels last night, you have my sympathies.  Perhaps during your rides into the conference, you can plan how to integrate data mining and revenue management better in order to let hotels avoid these issues in the future.

Did you like this? Share it:

From 2010 Annual Meeting Blogposts

  1. Golbon Zakeri permalink

    Very interesting Mike. One other point that comes to mind is that offering discounts may not be as effective for a conference crowd who would charge the room fee to a grant either! :)

  2. George Konstantinow permalink

    Great observations, Mike. I too think about Revenue Management whenever I fly, check in to a hotel, visit the clinic.

    What’s interesting to me is that, of all OR disciplines, Revenue Management seems the most *personal* - the issues are close to me, the problems are anecdotal, and the solutions are mysterious (unless you know the secret!).

    As to the disconnect - RM is is personal but DM is not. Few of us have access to the data, hence have nothing to mine, connect, or ponder. Imagine how different the hotel or healthcare experience would be if we dumb ol’ consumers could run our own algorithms, see the other guys’ cards, and up the ante in our day-to-day negotiations. Imagine the look on that hotel staffer’s face if you were to offer him/her a counter-incentive to let you in!

Trackbacks & Pingbacks

  1. Michael Trick’s Operations Research Blog : INFORMS Blog entry on “Overbooking, Revenue Management, and Data Mining”