Anomaly Detection in Public Procurements using the Open Contracting Data Standard

Abstract

The detection of anomalies in public procurements can enable the improvement of the quality of purchases, and consequently enable a better quality of life in the country through the correct use of public funds. In this paper, we use as a case study the public procurement data from Paraguay, available in the open data format of the Open Contracting Data Standard, to train an unsupervised learning model for anomaly detection based on the Isolation Forest algorithm. The Open Contracting Data Standard allows the developed technique to be replicated in other countries that implement the same data standard, thus achieving an interoperable solution. The resulting classification enables the scoring of contracts and procurement processes which can be used to identify anomalies and make it possible to obtain an intelligent sampling of the data. This can be utilized as a support in the task of the government in its role to regulate and control the public procurements. The effectiveness of the model is validated with local known anomalous procurement processes, which are: a)processes protested by entities involved in the contracting process, which were determined in favor of the protestant, and b)complaints about the contracting process from external entities with the possibility of anonymity. The results show an accuracy of over 90 % in detecting these known anomalies as early as in the tender stage and during the contracting stage. Thus indicating a feasible approach for anomaly detection in public procurements.