Contributing to the analysis of quantitative indicators (red flags) to detect corruption risks, the paper verifies the presence of several red flags (some known in the literature, others new) in a sample of Italian awarding procedures for public works. Then, it validates the efficacy of the indicators through measures of direct corruption risks (judiciary cases and police investigations for corruption-related crimes) and indirect corruption risks (delays and cost overruns).
The red flags related to discretionary mechanisms for selecting private contractors (such as the most economically advantageous offer or negotiated procedures), compliance with the minimum time limit for the submission of tenders and subcontracting are the most effective in detecting corruption risks. Prediction approaches based on machine learning methods (especially the random forests algorithm) are particularly relevant for validating a large set of indicators.
