Development of recursive decision making model in bilateral construction procurement negotiation

• A multi-strategy Bayesian fuzzy game model for optimizing a negotiation price is proposed.
• Detailed calculations are presented for two possible negotiation scenarios.
• Significant improvement in the estimation ability of negotiators is validated.
• The missing valuable information for Bayesian learning is effectively handled by proposed model.

Price negotiation in construction procurement is a form of decision making where contractor and supplier jointly search for a mutually agreed solution. In price negotiation, with information available about the agent's preferences, a negotiation may result in a mutually beneficial agreement. However, self-interested agents may not be willing to reveal their preferences, and this can increase the difficulty of negotiating a beneficial agreement. In order to overcome this problem, this paper proposes a Bayesian-based approach which can help an agent to predict its opponent's preference in bilateral negotiation. The proposed approach employs Bayesian theory to analyze the opponent's historical offers and to approximately predict the opponent's preference over negotiation issue. A Nash equilibrium algorithm is also integrated into the prediction approach to help agents on how to propose beneficial offers based on the prediction results. Validation results indicate good performance of the proposed approach in terms of utility gain and negotiation efficiency.