Demand modeling of stochastic product diffusion over the life cycle

Planning during the product life cycle (PLC) poses a number of challenges for managers due to the pace of change and uncertainties in the marketplace. The ability to better understand, predict, and make decisions based on manifestations of demand forms a set of important operational problems that ultimately affect the profitability of enterprises. This paper models the stochastic diffusion of a product in the market as a geometric Brownian motion (GBM) process that has a time-varying drift rate. The model is calibrated such that model parameters are able to feature different product types and diffusion conditions. Imperfect information on the expected peak demand is treated as model uncertainty, and a Bayesian approach is employed to update knowledge on it. The demand model demonstrates robust performance over a wide range of conditions despite model uncertainty. It provides both qualitative and quantitative information for manufacturers and service providers to design strategies for stochastic PLC conditions as well as dynamic production planning.