The country's five major coin exchanges will utilize artificial intelligence to detect and prevent market manipulation. This move comes as part of an effort to strengthen surveillance of the digital asset market. According to the Digital Asset Exchange Alliance on the 27th, the five major exchanges, including Upbit, Bithumb, Coinone, Korbit, and Gopax, have decided to apply AI-based market manipulation detection systems. The exchanges plan to use machine learning algorithms to analyze abnormal trading patterns and detect market manipulation in real-time. Previously, it took about three days to analyze suspicious transactions in depth, but with the new system, this process will be shortened to about one hour. The exchanges also plan to share information on suspicious transactions and collaborate with the authorities in charge of on-site inspections. An official from the exchange alliance said, "We expect that the AI-based market manipulation detection system will play a significant role in preventing market manipulation and enhancing market fairness." The introduction of the new system is also seen as a move to preemptively respond to the government's plan to strengthen regulations on the digital asset market. The Financial Services Commission announced on the 25th that it will establish a digital asset market abuse prevention and detection system and strengthen regulations on unfair trading. The government plans to revise the Virtual Asset Service Provider Guidelines to require exchanges to monitor and report suspicious transactions. The five major exchanges are also expected to expand their surveillance of digital assets. Currently, each exchange is conducting its own surveillance of digital assets, but there are limitations in terms of technology and manpower. The exchange alliance plans to support the improvement of the digital asset market by strengthening the exchanges' autonomous surveillance capabilities. The alliance also plans to establish a digital asset market monitoring system that can respond to changes in the market and provide support for the government and the industry.
South Korean virtual asset exchanges have implemented an automated market surveillance process utilizing artificial intelligence and machine learning algorithms to combat unfair trading practices. This system, dubbed 'Virtual Asset Illicit Trading Market Surveillance Process Automation,' can now analyze trading data in real-time and conduct in-depth analysis within an hour, down from the previous three days.
The Financial Supervisory Service of South Korea (FSS) has incorporated generative AI and machine learning algorithms into this automated system, which now scrutinizes the trading activities of five major virtual asset exchanges – Upbit, Bithumb, Coinone, Homeplus, and Gate.io – across approximately 2,000 virtual assets.
The primary focus of this advanced scrutiny is to detect potential instances of market manipulation, such as pump and dump schemes and order spoofing, which previously took a significant amount of time to investigate due to the extensive volume of data involved. Using AI algorithms, the system can now detect abnormal trading patterns, such as artificial inflation of trading volume or distortion of prices, as well as identify malicious content generated from online news, social media posts, and videos. These AI-driven algorithms can process up to tens of gigabytes of data during the analysis period.
Once the system flags a suspicious activity, it sends the relevant trading records to the virtual asset exchange for further examination. The examination involves a comprehensive analysis of account-specific order and settlement records. The FSS has confirmed that the system not only helps in identifying clear cases of illicit trading but also enables screening of borderline cases that may have been previously overlooked. In some instances, the system has even led to actual investigations based on the detected patterns.
Written by urgent.news from Hankyoreh's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
