Bank of America Corporation (20240232891). BLOCKCHAIN-BASED DIGITAL TRANSACTIONAL SYSTEM WITH MACHINE-LEARNING (ML)-POWERED RULE GENERATION simplified abstract
Contents
BLOCKCHAIN-BASED DIGITAL TRANSACTIONAL SYSTEM WITH MACHINE-LEARNING (ML)-POWERED RULE GENERATION
Organization Name
Inventor(s)
Mardochee Macxis of Concord NC (US)
Monika Kapur of Jacksonville FL (US)
Albena Fairchild of Indian Trail NC (US)
Utkarsh Raj of Charlotte NC (US)
BLOCKCHAIN-BASED DIGITAL TRANSACTIONAL SYSTEM WITH MACHINE-LEARNING (ML)-POWERED RULE GENERATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240232891 titled 'BLOCKCHAIN-BASED DIGITAL TRANSACTIONAL SYSTEM WITH MACHINE-LEARNING (ML)-POWERED RULE GENERATION
The patent application describes systems and methods for fraud prevention in a blockchain-based digital transactional system using machine-learning-powered rule generation.
- Creating a distributed ledger with foundational transactional parameter rules and historical transactional data in digital blocks.
- Hosting machine learning models on nodes to generate new transactional parameter rules.
- Adding new transactional parameter rules to the distributed ledger in response to a consensus.
- Running machine learning models to generate a probability score for fraudulent activity associated with additional transactional data.
- Triggering alerts for accounts associated with the additional transactional data if the score exceeds a predetermined threshold.
Potential Applications: - Financial transactions - E-commerce platforms - Cryptocurrency exchanges
Problems Solved: - Fraudulent activities in digital transactions - Enhancing security in blockchain-based systems
Benefits: - Improved fraud detection capabilities - Enhanced security and trust in digital transactions - Real-time alerts for potential fraudulent activities
Commercial Applications: Title: "Enhancing Security in Digital Transactions Using Machine Learning" This technology can be utilized by financial institutions, e-commerce platforms, and cryptocurrency exchanges to enhance security and prevent fraud in digital transactions, ultimately improving customer trust and satisfaction.
Prior Art: Researchers can explore prior art related to fraud prevention in blockchain systems, machine learning in digital transactions, and distributed ledger technologies.
Frequently Updated Research: Stay updated on advancements in machine learning algorithms for fraud detection, blockchain security protocols, and real-time transaction monitoring systems.
Questions about Fraud Prevention in Blockchain-Based Systems: 1. How does machine learning enhance fraud prevention in digital transactions? Machine learning models analyze transactional data to detect patterns and anomalies indicative of fraudulent activity, improving fraud prevention capabilities. 2. What are the key benefits of using a distributed ledger for fraud prevention in blockchain systems? A distributed ledger ensures transparency, immutability, and consensus among network participants, enhancing security and trust in digital transactions.
Original Abstract Submitted
systems and methods for fraud prevention in a blockchain-based digital transactional system with machine-learning (ml)-powered rule generation are provided. methods may include creating a distributed ledger in which digital blocks may include foundational transactional parameter rules, and digital blocks may include historical transactional data. methods may include hosting ml models on the nodes, running each ml model to generate new transactional parameter rules, and adding the new transactional parameter rule as a digital block on the distributed ledger in response to a consensus. methods may include receiving additional transactional data, running each ml model to generate a score representing a probability that the additional transactional data is associated with fraudulent activity, and triggering an alert for an account associated with the additional transactional data in response to a consensus across the plurality of ml models that the score exceeds a predetermined threshold score.
