Advertisement

Research on Natural Language Processing in Financial Risk Detection

  • Wei-Yu ChenEmail author
  • Shing-Han Li
  • Yung-Hsin Wang
Conference paper
  • 28 Downloads
Part of the Communications in Computer and Information Science book series (CCIS, volume 1227)

Abstract

With the rise of electronic financial transactions, illegal financial activities have emerged in an endless stream. People have used illegal funds to conceal or cover up illegal sources of funds through small-value transfers, cash orders, traveler’s checks and other gold trading channels to evade supervision by government units. It isn’t easy to trace the information of these golden streams, because the flow of funds includes the source and destination of the wire transfer, the nature of the wire transfer and the relationship between the sender and the bank are very complicated and difficult to check. Natural language processing understands the meaning of people’s commands and inputs in a seamless and simplified way. Further, it can eliminate the mistakes caused by human beings and enable financial risk control personnel to find problematic transactions in a short period of time in a more efficient manner. This study uses BERT’s TensorFlow open source code and the test data set provided by Paysim to conduct risk model construction research.

Keywords

Financial risk detection Natural language processing Anti money laundering 

References

  1. 1.
    Jernite, Y., Bowman, S.R., Sontag, D.: Discourse-based objectives for fast unsupervised sentence representation learning. CoRR, abs/1705.00557 (2017)Google Scholar
  2. 2.
    Peters, M., et al.: Deep contextualized word representations. In: NAACL (2018)Google Scholar
  3. 3.
  4. 4.
    Salehi, A., Ghazanfari, M., Fathian, M.: In India, data mining techniques for anti money laundering. Int. J. Appl. Eng. Res. 12(20), 10084–10094 (2017)Google Scholar
  5. 5.
    Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. cs.CL/1810.04805v2 (2019)Google Scholar
  6. 6.
    Akbik, A., Blythe, D., Vollgraf, R.: Contextual string embeddings for sequence labeling. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 1638–1649 (2018)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Mass CommunicationChinese Culture UniversityTaipeiTaiwan
  2. 2.Department of Accounting InformationNational Taipei University of BusinessTaipeiTaiwan
  3. 3.Department of Information ManagementTatung UniversityTaipeiTaiwan
  4. 4.Department of Computer Science and EngineeringTatung UniversityTaipeiTaiwan

Personalised recommendations