Shorting Crypto Top Gainers with AI Scoring and Staged Adds

Summary

This strategy screens USDT perpetual contracts for strong 24-hour gainers, then collects open interest, funding rates, market capitalization, and daily candles. Hard filters remove crowded shorts, low open interest, and coins that have already pulled back. An AI model scores candidates across six factors, emphasizing the open-interest-to-market-cap ratio and bearish candle patterns; only high scoring candidates proceed to short entry. The trading workflow runs every fifteen minutes, while a separate monitor checks positions every five seconds.

Each initial position is fixed at 50 USDT, with up to two larger adds if price rises further, capping combined exposure at 500 USDT. Profit taking trails a drawdown after a specified profit threshold, and a manual percentage stop is available. The article provides rules and code excerpts rather than out-of-sample performance evidence. It warns that inverse additions magnify losses if a coin continues rising, making the approach vulnerable to persistent bull markets and unsuitable without careful risk controls.

Key ideas

• The system selects high gaining perpetual contracts and filters them using market positioning, funding, liquidity, and recent price retracement.
• An AI score combines six inputs, with leverage proxy and candle structure receiving the greatest emphasis.
• Separate workflows handle slower candidate selection and frequent position monitoring.
• The short strategy adds exposure as price rises, subject to a stated total position cap.
• Trailing profit protection and optional fixed stops address exits, but sustained rallies can still produce large losses.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.