A cheap trend‑following ETH/USDC bot with two models in the loop: what paper trading showed

说明与用途

该基于Base的ETH/USDC趋势跟踪机器人在纸面交易中未能超过简单持有策略。它每个会话切换两次，但始终落后于持有，且判断模型很少发出交易信号。推理成本相对于小额资本而言较高。

问题

The bot was designed to trend‑follow ETH/USDC on Base via Uniswap v3, but paper trading over several days showed it did not outperform simply holding the asset.

结果

The bot failed to beat a simple hold strategy in all paper sessions. Forecast rule prevented any trades; trend rule caused whipsaw losses. Inference costs were 5 % of $100 capital, 0.5 % of $1,000, and 0.05 % of $10,000, making the system expensive for small accounts.

工作流

• 1. Compute features every 60 s (EMA20 vs EMA50, recent returns, volatility, switching cost).
• 2. Send state to a judge model via HTTP API to answer four fixed questions (regime, 15‑min direction, moment quality, risk‑off).
• 3. Aggregate votes: require 5/6 or 3/4 agreements depending on preset.
• 4. Apply filters: EMA trend agreement, optional veto from a second model (DeepSeek).
• 5. Enforce hard limits (switches per day, minimum hold, loss halts, inference budget, data freshness).
• 6. Execute switch if all conditions met, using on‑chain quotes and simulated fills in paper mode.

证据

The bot holds one position, all of it either in ETH or in USDC, and switches sides when several independent checks agree.

来源

Every 60 seconds: 1. Code computes features… 2. A judge answers four fixed questions… 3. Votes… 4. Filters and a veto… 5. Hard limits…

来源

Under the forecast rule the bot never traded… Under the trend rule every arm switched exactly twice and every arm lost to holding.

来源

Inference is the only running cost, and it is a fixed number of dollars per month… On $100 the models eat the capital faster than any plausible edge.

来源