Overbooked flight probability problem

  • Context: Undergrad 
  • Thread starter Thread starter bluebear19
  • Start date Start date
  • Tags Tags
    Flight Probability
Click For Summary
SUMMARY

The discussion centers on the overbooking strategy employed by airlines, specifically analyzing a scenario where 40 tickets are sold for a flight with a capacity of 35. The probability of a passenger not showing up is estimated at 0.2, leading to an expected 32 passengers showing up. The probability of more than 35 passengers arriving is calculated at 0.0759. The key problem is determining the maximum compensation per bumped passenger that maintains the expected value of selling 40 tickets over 35, with the formula for expected compensation derived from the probabilities of different passenger show-up scenarios.

PREREQUISITES
  • Understanding of probability theory and expected value calculations
  • Familiarity with binomial distribution concepts
  • Basic knowledge of airline ticketing and overbooking strategies
  • Ability to perform calculations involving expected compensation
NEXT STEPS
  • Study binomial distribution and its applications in real-world scenarios
  • Learn about expected value calculations in decision-making processes
  • Research airline revenue management techniques and overbooking policies
  • Explore statistical software tools for probability analysis, such as R or Python's SciPy library
USEFUL FOR

Airline revenue managers, operations researchers, statisticians, and anyone interested in the economics of overbooking and passenger compensation strategies.

bluebear19
Messages
37
Reaction score
0
Airlines often overbook flights. You are a manager selling 40 tickets on a flight with a capacity of 35. You estimate the probability of a given passenger NOT showing up is 0.2.

I already calculated some parts of the problem:
1) how many passengers do you expect to show up = (.8)(40) = 32
2) what is the probability that more than 35 will show up = .0759

Problem:
Suppose a ticket sells for $300. What is the maximum cost per passenger who must be "bumped" (compensation paid to ticketed passenger who can't take the overbooked plane) such it is worth (expected value) to sell 40 tickets versus 35. (For simplicity assume that you still get your $300 from anyone who purchased a ticket and doesn't show up)

Thank you in advance!
 
Physics news on Phys.org
Let P(n) be the probability that exactly n people show up. The expected number of people you must compensate is
N = P(36) + 2P(37) + 3P(38) + 4P(39) + 5P(40)

For overbooking to 40 to be better than selling 35, NC < $300 * 5, where C is the total amount you must compensate passengers who are bumped.
 

Similar threads

  • · Replies 6 ·
Replies
6
Views
2K
Replies
5
Views
2K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 10 ·
Replies
10
Views
17K
  • · Replies 1 ·
Replies
1
Views
3K
Replies
3
Views
2K
Replies
3
Views
5K
  • · Replies 5 ·
Replies
5
Views
11K
  • · Replies 4 ·
Replies
4
Views
5K
Replies
1
Views
8K