Location-Based Distribution Estimation for Stochastic Bid Price Optimization

Abstract

Stochastic bid price optimization of truckload carriers in simultaneous independent transportation auctions requires estimating the probability distributions of the clearing prices. Historical data can be used for this purpose. The sole estimation method found in the literature for this problem setting only takes the length of the auction load into account. In this paper, we devise methods for load-specific parameter estimation by filtering out data coming from past auction loads with distant origin or destination locations. Through simulations, we demonstrate that our methods can improve the profitability of the carriers compared to the previously used method.