Fraud detection in telephone conversations for financial services using linguistic features
Bajaj, N., Goodluck Constance, T., Rajwadi, M., Wall, J., Moniri, M., Glackin, C., Cannings, N., Woodruff, C. and Laird, J. 2019. Fraud detection in telephone conversations for financial services using linguistic features. Neural Information Processing Systems - NeurIPS 2019. Vancouver, Canada 08 - 14 Dec 2019 AI for Social Good Workshop NeurIPS.
|Authors||Bajaj, N., Goodluck Constance, T., Rajwadi, M., Wall, J., Moniri, M., Glackin, C., Cannings, N., Woodruff, C. and Laird, J.|
Detecting the elements of deception in a conversation is one of the most challenging problems for the AI community. It becomes even more difficult to design a transparent system, which is fully explainable and satisfies the need for financial and legal services to be deployed. This paper presents an approach for fraud detection in transcribed telephone conversations using linguistic features. The proposed approach exploits the syntactic and semantic information of the transcription to extract both the linguistic markers and the sentiment of the customer’s response. We demonstrate the results on real-world financial services data using simple, robust and explainable classifiers such as Naive Bayes, Decision Tree, Nearest Neighbours, and Support Vector Machines.
|Conference||Neural Information Processing Systems - NeurIPS 2019|
|Publisher||AI for Social Good Workshop NeurIPS|
|Accepted author manuscript|
File Access Level
|Online||14 Dec 2019|
|Publication process dates|
|Accepted||28 Sep 2019|
|Deposited||12 Jan 2021|
|Web address (URL)||https://aiforsocialgood.github.io/neurips2019/acceptedpapers_track2.htm|
|Copyright holder||© 2019 The Authors|
2views this month
2downloads this month