Desenvolvimento de API para identificação de fraude PIX
The bank transactions via PIX are already a reality in the Brazilian's life. According to the data provided by Banco Central do Brasil, until 2021 december, almost 110 millions people have been used. This new technology has positive impacts in the life of tens of thousands of people everyday...
Na minha lista:
| Autor principal: | |
|---|---|
| Outros Autores: | |
| Formato: | bachelorThesis |
| Idioma: | pt_BR |
| Publicado em: |
Universidade Federal do Rio Grande do Norte
|
| Assuntos: | |
| Endereço do item: | https://repositorio.ufrn.br/handle/123456789/49075 |
| Tags: |
Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
|
| Resumo: | The bank transactions via PIX are already a reality in the Brazilian's life. According to the
data provided by Banco Central do Brasil, until 2021 december, almost 110 millions people
have been used. This new technology has positive impacts in the life of tens of thousands of
people everyday bringing more facilities in your payments. But the high number of frauds
starts to happen with the use of the tool. Whether for the robbery of information, security
fails, coercions or trys of induce the victims to errors, the number of bankary crimes
continues growing and challenging the professional who works in the technology security
area. In the main types of frauds involving the PIX use we have six communs forms. (i) fake
employee of the institution; (ii) fake sequestration; (iii) bug coup; (iv) use of phishing; (v)
social media cloning; (vi) use of social engineering. To decrease the incidence of these
crimes, the app’s proprietary enterprises who make PIX transactions have invested in new
anti-fraud algorithms. In front of the exposed, the objective of this academic work is describe
the API(Application Programming Interface) development experience, using the elements of
machine learning and artificial intelligence, to provide a predict informing if a type PIX
bankary transaction is fraudulent. Through this, it is possible for the registration to be
intercepted before a crime can be practiced. The results presented in chapter 5 will detail in
graphics the main indices that can lead to the interference of a fraudulent transaction. It will
be possible to understand how the API manipulates this data to provide a prediction, and
show the positive impact that an API anti-fraud brings to minimize the number of crimes. |
|---|