Learning logistic demand curves in business-to-business pricing

This work proposes an approximate Bayesian statistical model for predicting the win/loss probability for a given price in business-to-business (B2B) pricing. This model allows us to learn parameters in logistic regression based on binary (win/loss) data and can be quickly updated after each new win/loss observation. We also consider an approach for recommending target prices based on the approximate Bayesian model, thus integrating uncertainty into decision-making. We test the statistical model and the target price recommendation strategy with synthetic data, and observe encouraging empirical results.