The Brazilian competition on Knowledge Discovery in Databases(KDD-BR) was firstly launched

in the 2017 joint editions of the Brazilian Conference on Intelligent Systems (BRACIS), the Brazilian Symposium on Databases (SBBD) and the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe), at Uberlândia-MG, Brazil.

This first edition involved classifying images captured by one of the monitoring stations of the EXOSS Citizen Science organization, which monitors meteors crossing the southern skies. The second edition was held in partnership with the IBM research center in São Paulo, as part of the BRACIS and KDMile events. The objective was to predict the production of palm oil harvests from the company Agropalma.

In 2019, the competition involved predicting the similarity between the partitions produced by the manual clustering of a set of molecular markers and those obtained by an auto-clustering tool, using data provided by the Corteva Agriscience company. Last year, the challenge involved predicting the unavailability of cars in a car rental agency using data provided by the Localiza Hertz company.

This year, the fifth edition of the KDD-BR competition will be one of the activities of the BRACIS conference, which will take place online, from November 29th to December 3rd, 2021.

2nd Call for Participation: KDD-BR 2021

News (1): top three teams will get a free registration to present their solutions at BRACIS 2021.News (2): top three teams will be invited to submit a short paper to ENIAC 2021 describing their solutions.

5th KDD-BR (Brazilian Knowledge Discovery in Databases) competition: AI-based approaches to predict solutions of the Travelling Salesman Problem

The 5th KDD-BR (Brazilian Knowledge Discovery in Databases) competition is one of the joint activities of the 2021 edition of BRACIS (Brazilian Conference on Intelligent Systems), which will organized by the Center for Artificial Intelligence (C4AI) from Universidade de São Paulo, SP, Brazil, from November 29th to December 3rd, 2021.

The objective of this year’s challenge is to develop a method to predict the edges belonging to solutions at tan problems. The traveling salesman problem (TSP) was first proposed in the 1930s, and it is among the most studied problems in combinatorial optimization and operational research, belonging to the class of routing problems.

The dataset contains 100k training examples of TSP problem-solution pairs ranging from 50 to 200 city nodes and was provided by the Loggi company.

The top three teams will be invited to present their solutions at a competition award session at the BRACIS 2021 conference, will receive a free registration pass to present their solutions of the Travelling Salesman Problem

Kaggel Site: https://www.kaggle.com/c/kddbr-2021

KDD-BR 2021 Site: http://c4ai.inova.usp.br/bracis/kdd.htm

Important Information:

– The dataset is available now at https://www.kaggle.com/c/kddbr-2021

– The solution submission deadline is: November 1st, 2021 (anywhere on Earth)

– The final results will be based on the solutions posted until November 1st, 2021. The actual final positions of the ranking will be disclosed during the event.


All members of the top three teams will have their registration free of charge at the conference.

Furthermore, thanks to the Loggi company, the award by each team will be:

The 1st place
R$ 500.00

The 2nd place
R$ 300.00

The 3rd place
R$ 200.00

KDD-BR Organization

Ana Carolina Lorena, Computer Science Professor at Instituto Tecnológico de Aeronáutica (ITA)

Filipe Alves Neto Verri, Computer Science Professor at Instituto Tecnológico de Aeronáutica (ITA)

Tiago Agostinho de Almeida, Computer Science Professor at Universidade Federal de São Carlos (UFSCar)

Gabriela Surita (Loggi)

Ângelo Gregório Lovatto (Loggi)

Regiane Nascimento (Loggi)

Tiago Leite (Loggi)

Fillipe Goulart (Loggi)

Juan Camilo Fonseca-Galindo(Loggi)

BRACIS 2021 – General Chairs

Reinaldo A. C. Bianchi, Centro Universitário FEI and C4AI

Zhao Liang, Universidade de São Paulo (USP) and C4AI


Organized by

Supported by