In the business and operational research field there is a class of per
ishable inventory control problems called 'yield management'. Examples
are floating pricing strategies in air ticket reservation and hotel r
oom booking. Due to the complex nature of yield management, there are
few analytical models available for practical application. This paper
presents a neural network approach to solving yield management problem
s. Using modified back propagation neural networks, a threshold band i
n the high-dimensional yield management space is generated based on hi
storical data and/or management expertise. When the actual inventory l
evel is outside the threshold band, prices should be adjusted to lead
the inventory level back to the threshold band. The interval of the th
reshold band indicates the stability of the business system.