AI-Assisted Polymarket Event Selection with K-Line Filters and Trailing Stops
Summary
This Polymarket strategy screens event contracts for liquidity, trading activity, spread, market competitiveness, and price, then scores hourly candlestick patterns such as gradual rises, growing volume, narrowing pullbacks, and breakouts. Candidates passing the technical screen receive a multi-role AI review of price and volume behavior, news support, estimated probability, and a final trade decision. Expiry rules constrain assessments near settlement. When several candidates qualify, the system selects one using confidence, degree of perceived underpricing, and probability-estimate precision.
The risk process checks positions frequently, applies a trailing stop based on the highest observed price with an entry-relative floor, and redeems eligible settled positions. The document describes workflow rules and thresholds, but supplies no performance results or evidence that AI probability estimates predict outcomes. Risks include thin liquidity, delayed or poor news analysis, rapid price convergence near expiry, and losses when chart patterns fail. The strategy also depends on platform access, external news search, and configured account and service credentials.
Key ideas
- The strategy filters event contracts by liquidity, volume, spread, competitiveness, and implied probability before analyzing price patterns.
- Hourly candle anomalies must meet a minimum combined score to advance to AI review.
- Four AI roles assess capital behavior, news, fair probability, and whether to trade, with expiry rules limiting late-stage trades.
- Only one candidate is selected per cycle, and open positions are managed with trailing stops and automatic redemption.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.