Identificação de manipulação no mercado financeiro de ações e derivativos por Spoofing e Layering

• Ano de defesa: 2019
• Autor(a) principal: Saldanha, Mateus Alves
• Orientador(a): Omar, Nizam
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Presbiteriana Mackenzie
• Palavras-chave em Português: manipulação; Spoofing Layering; mercado; Machine Learning; Market Data; Renda Variável; Adaboost, kMeans; Apriori
• Área do conhecimento CNPq: CNPQ::CIENCIAS SOCIAIS APLICADAS::CIENCIA DA INFORMACAO
• Link de acesso: http://dspace.mackenzie.br/handle/10899/24501

This research presents the study on the financial market of Brazil Stock Exchange for Bovespa and BMF segments, observing the mechanics of the sending of orders of the assets and the possibility of manipulation of the market. It presents the development of the stock market in Brazil and applying the American standards of financial market monitoring to identify manipulation of the stock market. Using the flow of liquid and illiquid instruments from both markets, evaluated the implementation of supervised and unsupervised machine learning techniques to identify manipulative behaviors. The project made use of the Python language, for the handling, analysis and presentation of the results.