20240037543. SYSTEMS AND METHODS FOR ENTITY LABELING BASED ON BEHAVIOR simplified abstract (Coinbase, Inc.)
Contents
SYSTEMS AND METHODS FOR ENTITY LABELING BASED ON BEHAVIOR
Organization Name
Inventor(s)
Alex Reeve of San Francisco CA (US)
Harrison Dahme of Stateline NV (US)
Linwei Chen of New York NY (US)
Ming Jiang of Foster City CA (US)
Zhicong Liang of Seattle WA (US)
SYSTEMS AND METHODS FOR ENTITY LABELING BASED ON BEHAVIOR - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240037543 titled 'SYSTEMS AND METHODS FOR ENTITY LABELING BASED ON BEHAVIOR
Simplified Explanation
The patent application describes methods and systems that utilize a second dataset, consisting of independently validated data from labeled blockchain operations, to identify and label suspicious blockchain operations. This is achieved by combining the second dataset with a dataset of labeled blockchain characteristics data obtained from multiple sources. The system employs a machine learning model to analyze the comprehensive input and detect fraudulent, criminal, or suspicious transactions. If a behavior type is deemed high risk by the model, the system can send an alert to the user and hold the associated funds in a separate account for manual review.
- The system uses a second dataset of independently validated data from labeled blockchain operations.
- The second dataset is combined with a dataset of labeled blockchain characteristics data from multiple sources.
- A machine learning model is employed to analyze the combined dataset and identify suspicious blockchain operations.
- Alerts can be sent to users when a high-risk behavior type is detected by the model.
- Funds associated with suspicious transactions can be held in a separate account for manual review.
Potential Applications:
- Fraud detection and prevention in blockchain transactions.
- Enhancing security and trust in blockchain networks.
- Compliance monitoring for financial institutions and regulatory bodies.
Problems Solved:
- Mitigating fraudulent, criminal, or suspicious transactions in blockchain networks.
- Improving the accuracy and efficiency of identifying suspicious behavior in blockchain operations.
- Reducing the risk of financial losses and reputational damage caused by fraudulent activities.
Benefits:
- Early detection and prevention of fraudulent transactions.
- Enhanced security and trust in blockchain networks.
- Improved compliance with regulations and industry standards.
- Reduction in financial losses and reputational damage.
- Efficient and automated identification of suspicious behavior in blockchain operations.
Original Abstract Submitted
methods and systems use a second dataset comprising independently validated data based on labeled blockchain operations previously processed through the blockchain network. the use of the second dataset in conjunction with the dataset comprising labeled blockchain characteristics data received from a plurality of sources provides a comprehensive input for a machine learning model to identify and label suspicious blockchain operations. by doing so, the system mitigates fraudulent, criminal, or suspicious transactions. for example, the system may send an alert to a user if a behavior type is deemed a high risk by the machine learning model; the system may furthermore hold the funds associated with the blockchain operation in a separate account while the transaction is manually reviewed. thus, the system may generate alerts to notify a user of a suspicious behavior type or suspicious blockchain operation, divert funds associated with the transaction, and conduct a manual review of suspicious blockchain operations.