Process for performance evaluation of Brazilian ESG financial investiments with scrapy and machine learning


The adoption and growth of ESG Investments in the financial markets of different countries in recent years demonstrate a strong tendency of companies and investors to act with investments that aim at both profit and long-term sustainability. Developing countries like Brazil currently have timid investments compared to European and North American countries, but have the potential to benefit given the social challenges and economic growth with sustainability that affect them. Such demand highlights the benefits and challenges that involve the machine learning pipeline to support the growth and development of ESG investments in a plural and global way, especially in countries with a natural language other than English, involving data tracking, creation of metrics and the prediction of long-term return on investment. The objective of this article is to propose a process that covers the collection, organization, training and evaluation phases of ESG investments focused on Brazil using machine learning models based on a systematic literature review. The results obtained showed that the systematic review presents relevant solutions to mitigate the complexity of ESG financial investments and shows that the set of neural network models such as LSTM, which is also part of the machine learning universe, are the most suitable for both sentiment analysis , classification and prediction of ESG investments.

GONÇALVES, Claudene Oliveira; GAVA, Vagner Luiz. Processo para avaliação de performance de investimentos financeiros ESG brasileiros com scrapy e machine learning. In: INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS AND TECHNOLOGY MANAGEMENT, 19.CONTECSI, 2022, São Paulo. Proceedings… São Paulo: FEA, 2023. 19p.

Document with restricted access. Login to BiblioInfo, Library/DAIT/IPT:

SUBSCRIBE to our newsletter

Receive our news in your email.

INSCREVA-se em nossa newsletter

Receba nossas novidades em seu e-mail.

Skip to content