| 摘要 |
A method of reducing financial fraud by operating artificial intelligence machines organized into parallel sets of predictive models with each set specially trained with supervised and unsupervised training data filtered for a particular financial channel. Each set integrates several artificial intelligence classifiers like neural networks, case based reasoning, decision trees, genetic algorithms, fuzzy logic, business rules and constraints, smart agents and associated real-time profiling, recursive profiles, and long-term profiles. Suspicious and abnormal activities in any channel communicate across predictive models for all the financial channels through real-time memory storage updates to the smart agent profiles they all share. |
| 主权项 |
1. A method of operating an artificial intelligence machine to reduce financial losses due to fraud, comprising:
sorting an instant transaction record received from a financial network according to a vertical business financial transactional channel with at least one processor that executes an algorithm to sort transaction records according to information within the transaction records that identifies a region and a vertical business financial transactional channel, and that further identifies an accountholder, merchant, or other entity; selecting with the at least one processor and an algorithm that trains a predictive model with supervised and unsupervised data previously filtered with a corresponding region and vertical business financial transactional channel identified in the instant transaction record in the step of sorting; classifying the instant transaction record with the at least one processor and an algorithm that obtains a decision from both a predictive model selected and a smart agent profile identified with the accountholder, merchant, or other entity in the step of sorting; updating the smart agent profile with the at least one processor and an algorithm that uses the decision obtained in the step of classifying to adjust the smart agent profile identified with the accountholder, merchant, or other entity in the step of sorting; accumulating decisions obtained in the step of classifying with the at least one processor and an algorithm that orders the accumulated decisions by the accountholder, merchant, or other entity identified in the step of sorting, wherein an accumulation of decisions provides a 360-degree view of all transactions occurring with each individual accountholder, merchant, and other entity; and automatically declining in real-time with the at least one processor and an algorithm that limits any future transactions of an individual accountholder, merchant, and other entity according to the 360-degree view. |
