Reverse Auction Bidding - Bid Arrivals Analysis

Reverse Auction Bidding (RAB) is a recently developed procurement method that can be used by the construction industry. The technique is different from a traditional auction system, since RAB system uses a bidding activity method that is completed anonymously by pre-qualified bidders during a fixed auction time. The basic premise for the auction is that the current best auction price is available for viewing during the whole auction process by both bidders and owner. The apparent incentive is for noncompetitive bidders to lower the price. There are however controlling factor beyond the reach of owners, such as market demand, lending restrictions, stakeholder expectations and risk tolerance levels, that impact on price levels. However, owners continue to attempt to drive down prices using this technique.

A study into the mechanics of RAB was launched at Texas A&M University in 2004. This ongoing study of RAB continues to this time with eighteen case studies. This nineteenth study looks at the time series bid data from some of the prior work. Nine case studies were selected from the previous case studies. These nine studies provided untainted data with 6674 RAB bid arrivals by prior investigator actions. This study concerns the statistical process of bid arrivals with time.

The hypothesis to be tested is that the RAB bid arrivals timing can be modeled with a statistical process. The analysis reviewed the fit for several types of distribution, including Gaussian and Poissionian. The best fit was modeled by non-homogeneous Poisson process (NHPP). The first conclusion from the analysis is that RAB bid arrivals follows a Poisson process, termed non-homogeneous Poisson process (NHPP). The second conclusion is that the controlling Poissionian process has a square root factor. The NHPP model for RAB provides a tool for future studies of RAB in real time. Future work is suggested on the inter-time periods for the bidding.