A robust dynamic pricing approach that tracks the customer´s imputed valuation

We present a robust dynamic pricing approach which seeks to offer prices that can become the actual sale prices, inasmuch as they are at or below the customer´s imputed valuation. The customer´s maximum buying prices are imputed since they are unknown; indeed, no historical demand data are provided. The only information that we are given in each time epoch is how much of the product is sold at a sale price offered by the seller, based on the remaining time, the level of product inventory, and whether the amount sold to date is more or less than the cumulative average amount. The proposed approach is quite successful in finding and tracking the imputed customer valuation curve over a finite time horizon. The results demonstrate the superiority of the approach not only in terms of revenue generation, but also in terms of four other effectiveness measures developed herein. The approach is especially well-suited for e-commerce.