Speaker: Milad Khaki, PhD Candidate
The project involves the analysis of procurement auctions for water infrastructure maintenance projects for Cities of Niagara Falls and London. The primary concern of this proposal is to generate a reliable mechanism for importing different formats of the tender summaries, provided as input data, of the projects and unify them in a database for further exploration and processing. For this part of the research, I developed a water infrastructure ontology to standardize the different aspects of the knowledge available in this field, which would eventually help us to import the data and look for any contextual inconsistencies and errors and act appropriately to repair them.
The next part of the project, the primary focus the study, is to analyze the historical auction data to extract various valuable pieces of information from them such as inflation rate and unit project prices. Also, it is possible to look into generating a profile of each recurrent bidder (contractor) and establish the statistical likelihood model of their behaviour. Therefore, any future auction can be inspected and compared to these profiles and any discrepancies or unexpected or highly unlikely behaviour that would raise a red flag can be found for further investigation. A comprehensive list of features that can act as the indicators of bidder behaviour is presented in this proposal, as well. The preliminary goal is to minimize the probability of any possible collusion (or find them if any exists) and detect unusual behaviours that might exist in the procurement auctions.