Técnicas de inteligencia artificial para optimizar la eficiencia del procedimiento de selección para la contratación de obras públicas

Abstract

The present article proposes to design a model that provides a generic architecture which acts autonomously in public works contracting selection processes, in order to generate an automated decision criterion in the event of a tie. For the Simplified Tender selection process, in case of a tie, it is proposed to choose the bidder by means of an electronic lottery based on a controlled randomization system of encryption and transformation. For the Public Bidding selection process, in the event of a tie, the bidder is chosen by means of a predicted compliance index according to the behavior of the companies when executing similar infrastructure projects. To this end, a model that predicts the probability of success or failure of the bidder to execute a project before initiating it is generated, using artificial neural networks as an analysis tool. This paper reviews the common characteristics of artificial neural networks.