Public procurement systems are prone to risks such as collusion, contractual concentration, and irregular subcontracting, which undermine transparency and accountability. Traditional fiscal oversight approaches remain largely retrospective, limiting their ability to anticipate irregularities and prevent potential losses. Addressing the gap between theoretical machine learning models and real-world institutional deployment, this study introduces an applied system innovation that integrates two complementary approaches at a national scale: a Contractual Network Model (Mallas Contractuales) and a Predictive Risk Model for Contractors. The first component uses graph-based analytics, employing an Entity–Link–Property schema to represent relationships among entities, contractors, and contracts, thereby enabling the detection of structural patterns associated with collusive or anomalous behavior. The second component implements supervised machine learning models, trained on more than 16 million contracts and 2.6 million contractors from sources such as SECOP, RUES, DIAN, and national sanction registries. Models, including Random Forests and Gradient Boosted Trees, were optimized via cross-validated hyperparameter search and evaluated on a separate hold-out set using ROC AUC and Gini metrics, achieving strong discriminatory performance under the available retrospective validation setting while maintaining operational interpretability. Both approaches were deployed in a modular architecture that integrated Databricks, i2 Analyst’s Notebook, and Power BI dashboards, providing interactive visualizations and risk scores at multiple levels. Together, these systems demonstrate how the convergence of graph analytics and predictive modeling enables proactive fiscal auditing, strengthens institutional capacity, and offers a replicable framework for public sector accountability.
Cifuentes-Perdomo et al. (Thu,) studied this question.