Scan to download
BTC $77,532.58 -0.24%
ETH $2,315.23 +0.07%
BNB $637.23 +0.09%
XRP $1.43 +0.28%
SOL $86.31 +1.02%
TRX $0.3235 -1.24%
DOGE $0.0987 +0.86%
ADA $0.2512 +0.99%
BCH $454.66 -0.33%
LINK $9.41 +1.35%
HYPE $41.19 +0.22%
AAVE $94.62 +1.15%
SUI $0.9499 +0.65%
XLM $0.1728 -0.93%
ZEC $354.67 +3.50%
BTC $77,532.58 -0.24%
ETH $2,315.23 +0.07%
BNB $637.23 +0.09%
XRP $1.43 +0.28%
SOL $86.31 +1.02%
TRX $0.3235 -1.24%
DOGE $0.0987 +0.86%
ADA $0.2512 +0.99%
BCH $454.66 -0.33%
LINK $9.41 +1.35%
HYPE $41.19 +0.22%
AAVE $94.62 +1.15%
SUI $0.9499 +0.65%
XLM $0.1728 -0.93%
ZEC $354.67 +3.50%

edu

Coinbase upgrades its anti-fraud system, integrating machine learning with a rules engine, reducing response time to a few hours

Coinbase stated that it is optimizing the rule creation process in its anti-fraud system by integrating machine learning models with a rules engine, achieving more efficient risk management. It also proposed a dual-track strategy of "models responsible for long-term defense, rules responsible for rapid response," and built a unified framework to create a feedback loop between the two: rules are used to capture new types of fraud and train the model in reverse, thereby continuously enhancing overall defense capabilities.In terms of specific optimizations, Coinbase has transformed the previously manual rule creation process into a data-driven and automated recommendation system by restructuring data, automating schema evolution, and introducing notebook-based analytical tools, significantly improving efficiency. Among these improvements, the performance of rule backtesting has increased by more than 10 times, and the overall response time has been reduced from several days to a few hours. Additionally, the new system uses machine learning to recommend parameters, helping to reduce false positive rates while combating fraud and minimizing the impact on normal users. Coinbase indicated that the next step will be to advance event-driven automatic rule generation and explore the "one-click conversion" of efficient rules into model features, further moving towards an automated risk management system.

Spark's strategic director: The ETH market faces liquidity risks due to a potential 10% to 15% reduction in rsETH loans

The strategic director of Spark, monetsupply.eth, posted on platform X that as the stablecoin market begins to lack liquidity, the situation is entering a more dangerous phase. I believe that the ETH market is about 16.5% supported by rsETH, and if the loans supported by rsETH experience losses shared between the mainnet and external chains, there may be a 10% to 15% reduction in emode, leaving a remaining 2% to 3% reduction for ETH suppliers to smooth out the umbrella structure.ETH suppliers naturally tend to exit as soon as possible to avoid this risk, so the utilization rate is locked at 100%, and the borrowing rates are insufficient to incentivize the repayment of unrelated LST cycles (wstETH, weETH) to release liquidity. Since users cannot withdraw ETH, those who borrow stablecoins like USDT and use ETH as collateral cannot close their positions even when stablecoin borrowing rates rise, cutting off the typical incentive mechanism to maintain market health.Currently, two unhealthy incentives are causing the market utilization rate to be locked at 100%: 1) ETH holders cannot close their positions to maintain a healthy LTV, and liquidators cannot atomically withdraw or sell collateral, which may lead to bad debts if the ETHUSD price falls. 2) Users supplying USDT, in order to exit their holdings, tend to maximize borrowing of other stablecoins, which is currently generating positive returns (temporarily), thus the exit cost is low; if conditions worsen, they can at least recover 75% of the position value.The bottom line is that these pooled/re-staked lending markets must maintain liquidity at all costs to operate normally. The recent weakening of slope2 against Aave's maximum borrowing rate is having a negative impact and significantly increasing the risk of failure in the yield market.
app_icon
ChainCatcher Building the Web3 world with innovations.