A Bayesian Model for Optimal Bid Price Estimation for Transportation Projects


Transportation projects represent 42% of the total public construction projects in the US. With such immense size, proper competitive bidding is a must to ensure appropriate utilization of the taxpayer’s money. Contractors submitting low bid prices are awarded projects. However, they become claim-oriented to recover losses resulting from their unrealistic bids. This results in severe quality, schedule, and cost impacts. Several models have been developed to help contractors determine their bid prices based on statistical analysis of competitors’ history; however such models do not consider cases of imperfect information and dynamic behavior of competitors; where a competitor’s old behavior contradicts its more recent bidding strategies. This paper presents a Bayesian-based statistical model for optimal bid price determination that is valid in cases of incomplete historical data and dynamic behavior of competitors. The developed model is based on a three-step research methodology. The first step is fitting the competitors’ data into appropriate Bayesian prior density functions. The second step is developing the likelihood functions through the most recent historic observation(s). The third step is developing the posterior distributions from which the joint probability of winning and the expected profit can be calculated. The proposed model was applied to a case study from the literature. In such case study, the effects of the different parameters were demonstrated. The research will be beneficial to the transportation infrastructure economy by ensuring that contractors submit bids with reasonable prices; which will make them less susceptible to claim-oriented behavior, and eventually lead to healthier contracting environments.

Meeting Name

Transportation Research Board 96th Annual Meeting (2017: Jan. 8-12, Washington, DC)


Civil, Architectural and Environmental Engineering

Keywords and Phrases

Bayes' theorem; Case studies; Competitive bidding; Construction projects; Contractors; Estimating; Prices; Statistical analysis

Document Type

Article - Conference proceedings

Document Version


File Type





© 2017 Transportation Research Board, All rights reserved.

Publication Date

12 Jan 2017