WiMi Developed a Trimmed K-Means Algorithm to Detect Crypto Wallet Fraud on the Bitcoin Network

Beijing, Jan. 18, 2024 (GLOBE NEWSWIRE) -- WiMi Hologram Cloud Inc. (NASDAQ: WIMI) ("WiMi" or the "Company"), a leading global Hologram Augmented Reality ("AR") Technology provider, today announced a Trimmed K-Means algorithm for detecting crypto-wallet fraud on the Bitcoin network. It combines symmetry and asymmetry in computer and engineering sciences to provide a novel solution for crypto-wallet fraud on the Bitcoin network. The technology not only improves detection efficiency but also identifies anomalous behavior more accurately, providing a more secure trading environment for Bitcoin investors.

This algorithm has a wide range of potential for practical applications. First, through the collective anomaly detection method, anomalous behaviors can be identified more efficiently on the Bitcoin network, improving the overall security of the network. Second, the Trimmed K-Means algorithm is used to reduce the processing cost of feature extraction, making it more practical. In addition, the algorithm not only detects fraudulent behavior but also provides a more reliable trading environment for Bitcoin investment.

The core of WiMi's Trimmed K-Means algorithm is the symmetry and asymmetry of the blockchain. Symmetry, which means that a complete record of transactions is kept at each node, ensures decentralization. Asymmetry, on the other hand, manifests itself in the relative anonymity of each transaction participant, which provides potential room for fraudsters to hide. The algorithm better identifies anomalous behavior by analyzing the overall behavior of the user community.

Second, collective anomaly detection methods are used to detect anomalous behavior on the Bitcoin network more efficiently. Collective anomaly detection is a method that identifies anomalies in individual behaviors by analyzing overall behavioral patterns. On the Bitcoin network, it is relatively common for users to have multiple wallets, and fraudulent behavior is often reflected in the behavioral patterns of an entire group of users. Unlike traditional single-address and wallet anomaly detection methods, this algorithm captures potential crypto-wallet fraud more comprehensively by focusing on users' anomalous behaviors. This approach not only improves detection accuracy, but also reduces false reports.