In a technological world, in which data is generated exponentially, financial analysis has gradually become more important to avoid large losses due to fraud. Considering the large volume and the difficulty of human data checking, machine learning technologies have become one of the main tools to solve the problem. However, due to the creation of data protection laws in several countries, in some scenarios the detection of fraud through intelligence algorithms becomes insufficient. Therefore, it is necessary to understand how the algorithm actually labels a transaction as fraudulent or not. In this work, presented as a systematic literature review, we look for answers on how explicable/interpretable fraud detection algorithms have been applied in order to solve the problem of illegal activities in the financial sector. As a result of the mapping of the current state of the art, this work highlights the gaps in the literature and present the scenario of interpretable techniques used for fraud detection comprehension.
Em um contexto tecnológico, em que dados são gerados de maneira exponencial, as análises financeiras tem se tornado gradativamente mais importantes para evitar grandes perdas devido às fraudes. Neste trabalho, busca-se a segmentação das transações em grupos, por meio de técnicas de agrupamento, com base na existência de padrões distintos entre transações financeiras legítimas e ilegais. Para isto, algoritmos foram testados e comparados em relação ao desempenho, validação do agrupamento, interpretação e compreensão, sendo os três últimos critérios utilizados para a formulação de hipóteses. Como resultado espera-se uma redução do espaço de busca para que possíveis fraudes possam ser investigadas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.