Application Of Stochastic Approximation To Digital Knowledge Products Pricing In Electronic Commerce

It is very difficult to price thousands of digital knowledge products (DKP) dynamically reflecting all the products' characteristics and constraints by traditional pricing in electronic commerce. To solve this problem, we adopted a combined model approach that selected appropriate pricing models and integrated them. The three proposed models are cost-plus, customer-expectation and customer-consumption models. We adopted stochastic approximation to set weight. In particular, we considered the case in which automatic pricing was done in order to maximize the profit and the number of sale of an on-line marketing site. We described the concrete pricing algorithms, and reported on preliminary performance evaluation of experiments. The results of experimentation verify that our methods are practical in terms of both the speed of convergence to the optimal price and computational efficiency.