In this paper, an inventory model is developed for deteriorating items with stock-dependent demand,
permitting shortages and time-proportional backlogging rate. In particular, the backlogging rate is considered
to be a decreasing function of the waiting time for the next replenishment. This assumption is more
realistic. In practice, we can observe periodically the proportion of demand which would accept backlogging
and the corresponding waiting time for the next replenishment. Then the statistical techniques, such
as the nonlinear regression method, can be used to estimate the backlogging rate. The analytical formulations
of the problem on the general framework described have been given. The condition which guarantees
the unique solution is obtained and the complete proof of corresponding second-order sufficient
conditions for optimum is also provided.
Furthermore, the results of above sensitivity analysis are consistent with the intuitive reasoning. For
fixed b, the larger the value of d is, the smaller the proportion of customers who would accept backlogging
at time t. Hence, in order to maximize the profit per unit time, the retailer should add the fraction of each
cycle in which there is no shortage. We also find that the optimal profit per unit time with partial backlogging
is more sensitive to d when its value is small. As the value of d increases, the optimal profit per unit
time becomes close to the optimal profit per unit time without shortage