VigIA: prioritizing public procurement oversight with machine learning models and risk indices

Public procurement is a fundamental aspect of public administration. Its vast size makes its oversight and control very challenging, especially in countries where resources for these activities are limited. To support decisions and operations at public procurement oversight agencies, we developed an...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrés Salazar, Juan F. Pérez, Jorge Gallego
Format: Article
Language:English
Published: Cambridge University Press 2024-01-01
Series:Data & Policy
Subjects:
Online Access:https://www.cambridge.org/core/product/identifier/S263232492400083X/type/journal_article
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850132258508242944
author Andrés Salazar
Juan F. Pérez
Jorge Gallego
author_facet Andrés Salazar
Juan F. Pérez
Jorge Gallego
author_sort Andrés Salazar
collection DOAJ
description Public procurement is a fundamental aspect of public administration. Its vast size makes its oversight and control very challenging, especially in countries where resources for these activities are limited. To support decisions and operations at public procurement oversight agencies, we developed and delivered VigIA, a data-based tool with two main components: (i) machine learning models to detect inefficiencies measured as cost overruns and delivery delays, and (ii) risk indices to detect irregularities in the procurement process. These two components cover complementary aspects of the procurement process, considering both active and passive waste, and help the oversight agencies to prioritize investigations and allocate resources. We show how the models developed shed light on specific features of the contracts to be considered and how their values signal red flags. We also highlight how these values change when the analysis focuses on specific contract types or on information available for early detection. Moreover, the models and indices developed only make use of open data and target variables generated by the procurement processes themselves, making them ideal to support continuous decisions at overseeing agencies.
format Article
id doaj-art-3789ff48f2b44eea9566d22de611cbf8
institution OA Journals
issn 2632-3249
language English
publishDate 2024-01-01
publisher Cambridge University Press
record_format Article
series Data & Policy
spelling doaj-art-3789ff48f2b44eea9566d22de611cbf82025-08-20T02:32:15ZengCambridge University PressData & Policy2632-32492024-01-01610.1017/dap.2024.83VigIA: prioritizing public procurement oversight with machine learning models and risk indicesAndrés Salazar0https://orcid.org/0009-0002-1182-2926Juan F. Pérez1https://orcid.org/0000-0003-4732-1621Jorge Gallego2https://orcid.org/0000-0002-9398-9553Department of Economics, Universidad del Rosario, Bogotá, Colombia.Department of Industrial Engineering, Universidad de los Andes, Bogotá, ColombiaOffice of Evaluation and Oversight, Inter-American Development Bank, Washington, DC, USAPublic procurement is a fundamental aspect of public administration. Its vast size makes its oversight and control very challenging, especially in countries where resources for these activities are limited. To support decisions and operations at public procurement oversight agencies, we developed and delivered VigIA, a data-based tool with two main components: (i) machine learning models to detect inefficiencies measured as cost overruns and delivery delays, and (ii) risk indices to detect irregularities in the procurement process. These two components cover complementary aspects of the procurement process, considering both active and passive waste, and help the oversight agencies to prioritize investigations and allocate resources. We show how the models developed shed light on specific features of the contracts to be considered and how their values signal red flags. We also highlight how these values change when the analysis focuses on specific contract types or on information available for early detection. Moreover, the models and indices developed only make use of open data and target variables generated by the procurement processes themselves, making them ideal to support continuous decisions at overseeing agencies.https://www.cambridge.org/core/product/identifier/S263232492400083X/type/journal_articleGovTech solutionsmachine LearningPublic procurement
spellingShingle Andrés Salazar
Juan F. Pérez
Jorge Gallego
VigIA: prioritizing public procurement oversight with machine learning models and risk indices
Data & Policy
GovTech solutions
machine Learning
Public procurement
title VigIA: prioritizing public procurement oversight with machine learning models and risk indices
title_full VigIA: prioritizing public procurement oversight with machine learning models and risk indices
title_fullStr VigIA: prioritizing public procurement oversight with machine learning models and risk indices
title_full_unstemmed VigIA: prioritizing public procurement oversight with machine learning models and risk indices
title_short VigIA: prioritizing public procurement oversight with machine learning models and risk indices
title_sort vigia prioritizing public procurement oversight with machine learning models and risk indices
topic GovTech solutions
machine Learning
Public procurement
url https://www.cambridge.org/core/product/identifier/S263232492400083X/type/journal_article
work_keys_str_mv AT andressalazar vigiaprioritizingpublicprocurementoversightwithmachinelearningmodelsandriskindices
AT juanfperez vigiaprioritizingpublicprocurementoversightwithmachinelearningmodelsandriskindices
AT jorgegallego vigiaprioritizingpublicprocurementoversightwithmachinelearningmodelsandriskindices