Won't Get Fooled Again: A Supervised Machine Learning Approach for Screening Gasoline Cartels

51 Pages Posted: 26 Jan 2021

See all articles by Douglas Silveira

Douglas Silveira

University of Alberta - Department of Economics

Silvinha Vasconcelos

Universidade Federal de Juiz de Fora - Department of Economics

Marcelo Resende

Universidade Federal do Rio de Janeiro (UFRJ); CESifo (Center for Economic Studies and Ifo Institute)

Daniel O. Cajueiro

University of Brasilia - Department of Economics

Date Written: 2021

Abstract

In this article, we combine machine learning techniques with statistical moments of the gasoline price distribution. By doing so, we aim to detect and predict cartels in the Brazilian retail market. In addition to the traditional variance screen, we evaluate how the standard deviation, coefficient of variation, skewness, and kurtosis can be useful features in identifying anti-competitive market behavior. We complement our discussion with the so-called confusion matrix and discuss the trade-offs related to false-positive and false-negative predictions. Our results show that in some cases, false-negative outcomes critically increase when the main objective is to minimize false-positive predictions. We offer a discussion regarding the pros and cons of our approach for antitrust authorities aiming at detecting and avoiding gasoline cartels.

JEL Classification: C210, C450, C520, K400, L400, L410

Suggested Citation

Silveira, Douglas and Vasconcelos, Silvinha and Resende, Marcelo and Cajueiro, Daniel O., Won't Get Fooled Again: A Supervised Machine Learning Approach for Screening Gasoline Cartels (2021). Available at SSRN: https://ssrn.com/abstract=3770457 or http://dx.doi.org/10.2139/ssrn.3770457

Douglas Silveira (Contact Author)

University of Alberta - Department of Economics ( email )

Edmonton, Alberta T6G 2R6
Canada

Silvinha Vasconcelos

Universidade Federal de Juiz de Fora - Department of Economics

Juiz de Fora, Minas Gerais
Brazil

Marcelo Resende

Universidade Federal do Rio de Janeiro (UFRJ) ( email )

Rua Sao Francisco Xavier, 524
Instituto de Economia
Rio de Janeiro RJ 21949
Brazil

CESifo (Center for Economic Studies and Ifo Institute)

Poschinger Str. 5
Munich, DE-81679
Germany

Daniel O. Cajueiro

University of Brasilia - Department of Economics ( email )

Brazil

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
65
Abstract Views
292
rank
429,604
PlumX Metrics