The study of the football transfer market is relevant to understanding the clubs’ managerial capacity when they trade their most important assets. So far, the research on football transfers has focused mainly on the movements between European clubs. Thus, it is necessary to expand the analysis to developing countries, particularly those with a strong football tradition. We study the Brazilian professional football transfer market by analysing the transfers between top Brazilian clubs from 2018 to 2020. We use a two-step Heckman correction to account first for variables that affect the probability of a transfer and later, the actual transfer fee. We include an innovative index to capture the players’ ability to perform according to the specialists’ expectations. Our results show that besides appreciating the specific characteristics of the player such as age and nationality, the Brazilian market also considers the capacity of a player to fulfill previous expectations when deciding who is transferred and for what price. Finally, the remaining time of the contract and the recent transfer history of the player also affect transfer movements in Brazil, along with the seller club’s performance.
Sistemas de Alerta Antecipado (EWS) para crises cambiais é um tópico essencial em macroeconomia. renovado por métodos de aprendizado de máquina. A maioria dos trabalhos publicados tem métricas de precisão excessivamente otimistas causadas pela desconsideração da autocorrelação ou atrasos na publicação de dados. Nossa contribuição é construir um Sistema de Alerta Antecipado baseado em um conjunto de modelos de aprendizado de máquina apropriados para dados de séries temporais. Usando dados de 25 países entre 1995 e 2020, nossas descobertas são mais modestas do que trabalhos recentes, mas destacam a utilidade e as limitações dos sistemas de alerta antecipado na prática.