IFDDS: An Anti-fraud Outbound Robot

Authors

  • Zihao Wang Ant Group
  • Minghui Yang Ant Group
  • Chunxiang Jin Ant Group
  • Jia Liu Ant Group
  • Zujie Wen Ant Group
  • Saishuai Liu Ant Group
  • Zhe Zhang Ant Group

Keywords:

Outbound Robot, Dialogue System, Dialogue Policy, Dialogue Risk Detection

Abstract

With the rapid growth of internet finance and e-payment, payment fraud has attracted increasing attention. To prevent customers from being cheated, systems often block risky payments depending on a risk factor. However, this may also inadvertently block cases which are not actually risky. To solve this problem, we present IFDDS, a system that proactively chats with customers through intelligent speech interaction to precisely determine the actual payment risk. Our system adopts imitation learning to learn dialogue policies. In addition, it encompasses a dialogue risk detection module which identifies fraud probability every turn based on the dialogue state. We create a web-based user interface which simulates a practical voice-based dialogue system.

Downloads

Published

2021-05-18

How to Cite

Wang, Z., Yang, M., Jin, C., Liu, J., Wen, Z., Liu, S., & Zhang, Z. (2021). IFDDS: An Anti-fraud Outbound Robot. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16117-16119. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/18030