Authors:
Carlos Vinícius Sarmento Silva
1
and
Célia Ghedini Ralha
2
Affiliations:
1
Controladoria Geral da União (CGU), Brazil
;
2
University of Brasíılia, Brazil
Keyword(s):
Agent-mining tool, Brazilian government auditing, AGMI, e-Government.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
e-Business
;
Enterprise Information Systems
;
Government
;
Knowledge Management and Information Sharing
;
Knowledge-Based Systems
;
Social Information Systems
;
Society, e-Business and e-Government
;
Symbolic Systems
;
Web Information Systems and Technologies
Abstract:
This paper presents research combining two originally separated areas increasingly interrelated: distributed multi-agent systems and data mining. In our approach, we prove the interaction features in a bilateral and complementary way, since we have defined an integrated architecture and developed a prototype, which has been used in a government auditing study case. In Brazil, government auditing is performed by the Office of the Comptroller General (CGU), where several approaches are being used to prevent and fight corruption. However, some activities such as government purchasing fraud detection are limited by the difficulty in finding effective ways to implement. Considering data mining perspective, we have used different model functions, such as clusterization and link analysis with association rules. Our approach integrating multi-agent and data mining techniques resulted in expressive discovered knowledge, which would help detection of cartels acting in public bidding processes
at CGU.
(More)