The Application of Convolutional Neural Networks in Bidding Price Estimation Decision

In the daily bidding activities, the bid price is estimated by using qualitative and quantitative predicting methods, which are usually poor in accuracy and efficiency. In this paper, we introduce a method based on the Convolutional Neural Networks (CNNs) for the bid price estimation decision. We collect the historical bidding price data from similar projects and then form a time series according to the order of the project start time to extract deep CNN features, and tinally, these deep features are used to make bidding decision. We demonstrate that the learned deep models will help the decision makers to get the trend of project quotation and improve the bid winning probability and competitiveness of the bidder.