A Machine-Learning Approach to Optimal Bid Pricing

Abstract

We consider the problem faced by a seller in determining an optimal price to quote in response to a Request for Quote (RFQ) from a prospective buyer. The optimal price is determined by maximizing expected profit, given the underlying seller costs of the bid items and a computed probability of winning the bid as a function of price and other bid features such as buyer characteristics and the degree of competition. An entropy-based information-gain metric is used to quantify the contribution of the extracted features to predicting the win/loss label. A naive Bayes classification model is developed to predict the bid outcome (win or loss) as a function of these features. This model naturally generates the win probability as a function of bid price required to compute the optimal price. Results obtained by applying this model to a database of bid transactions involving computer sales demonstrate statistically significant lift curves for predicting bid outcome. A method for creating additional synthetic bids to improve computation of the win probability function is demonstrated. Finally, the computed optimal prices generated via this approach are compared to the actual bid prices approved by human pricing experts.