首页>
外国专利>
MACHINE LEARNING MODEL AND NARRATIVE GENERATOR FOR PROHIBITED TRANSACTION DETECTION AND COMPLIANCE
MACHINE LEARNING MODEL AND NARRATIVE GENERATOR FOR PROHIBITED TRANSACTION DETECTION AND COMPLIANCE
展开▼
机译:用于禁止交易检测和合规性的机器学习模型和叙事发电机
展开▼
页面导航
摘要
著录项
相似文献
摘要
There are provided systems and methods for a machine learning model and narrative generator for prohibited transaction detection and compliance. A service provider server, such as an electronic transaction processor, may generate a machine learning model using a supervised training technique, which may detect transactions that may be money laundering. The model may be iteratively trained by detecting flagged transactions and outputting those transactions to an agent for identification of false positives, which may be used to retrain the model. When outputting the flagged transactions, a narrative may be generated using an explainer graph and a machine learning prediction explainer that identifies the features of the transaction data that caused the transactions to be flagged. Further, once the model is trained additional transactions may be processed to determine whether the features of those transactions indicate prohibited behavior.
展开▼