Public big data platform for mapping signs of irregularity in company relationships with counterparties

• Grant number: 19/00804-9
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: October 01, 2019
• End date: September 30, 2021
• Field of knowledge: Applied Social Sciences - Administration - Business Administration
• Agreement: FINEP - PIPE/PAPPE Grant
• Principal Investigator: Lucas Madureira dos Anjos
• Grantee: Lucas Madureira dos Anjos
• Company: Gedanken Desenvolvimento e Licenciamento de Programas de Computador Ltda
• CNAE: Desenvolvimento e licenciamento de programas de computador customizáveis ; Desenvolvimento e licenciamento de programas de computador não-customizáveis
• City: Ribeirão Preto
• Associated researchers: André Luiz Martins Pignata ; Luciana Oranges Cezarino ; Rafael Madureira dos Anjos ; Rodrigo Palucci Pantoni
• Associated scholarship(s): 19/25945-4 - Public big data platform for mapping signs of irregularity in public procurement, municipal comparison and effectiveness of public spending, BP.TT; 20/00012-2 - Public big data plataform: predicting public procurement irregularity, city comparison and public cost effectiveness, BP.TT

Abstract

This project proposes the development of a big data platform based on structured and unstructured public and private data and artificial intelligence to assist public and private companies and large companies to drastically reduce irregularities not only in their hiring, but also in their relationships with public agencies, business partners and customers. The platform to be developed will work integrated with ERP (Enterprise Resource Planning) - Integrated Business Management System - of large companies, reading each payment made to a counterparty, be it a supplier, employee, commercial partner or public agency, and assigning a risk score based on algorithms that cross a large number of databases and behaviors. Every high-risk appointment is smoothed out by a compliance specialist from the company itself, who confirms or not that indication of irregularity. With this information, the platform's algorithms learn and start making increasingly assertive decisions. The platform is based on the first phase of the project in which 9 robots were identified to identify signs of irregularities that mapped more than one million traces of possible deviations in municipal contracts, based on the studied, captured, organized and treated only municipal payments from the State of São Paulo to each of its suppliers. The basis for technological development is the same, but now it is no longer applied to each of the municipal payments, but to payments made by large companies to their counterparts. (AU)