A Study on Optimizing Price Using Business Rule as a Prior

This study tries to propose the new model to have more accurate price optimization for a specific business. Usually the optimal pricing solutions which come from the estimated sales models suggest prices that are unfairly inaccurate, which leads the manager to come up with some decision rules and constraints on the shelf price as a more appropriate solution. Using this information as a post hoc instead of prior information leads to inefficient pricing decisions. This study tries to use manager’s constraints on the price solution as a prior information about the model. The study argues that the model and its prior (Business Rules about optimal prices) can be translated into informative prior distributions. These prior distributions appropriately weight the managerial knowledge against the data unlike the traditional approach. Moreover, this study considers situations in which the analyst may not know either the business rule or model with complete certainty of demand and illustrate the impact of this uncertainty on the optimal pricing solution using Bayes theorem by conducting Monte Carlo algorithm.