EMA Crossovers Combined with News Sentiment for Crypto Perpetuals
Summary
This workflow describes an automated crypto perpetual-futures system that combines short- and long-term EMA crossovers with news sentiment. It evaluates completed candles to identify golden or death crosses, then gathers recent RSS coverage and has an AI model score news for relevance, direction, and freshness. Coin-specific stories receive the greatest weight, while broader market, major-asset, regulatory, and industry news can also affect the assessment.
A decision matrix uses the technical signal, sentiment level, current position direction, and unrealized profit or loss to choose whether to open, add to, partially close, fully close, or retain a position. Order execution includes checks for position caps, exchange minimum order value, and valid close quantity. The workflow also describes persistent trend state and a monitoring panel for account, position, decision, and execution status. These are design details rather than empirical findings: no backtest results or live trading evidence are supplied. The approach depends on the quality and timeliness of news feeds and AI interpretation, and its directional rules do not establish that sentiment agreement improves returns.
Key ideas
- Completed candles are used for EMA crossover detection to avoid acting on an unfinished bar.
- News is weighted by asset relevance, broader market impact, and recency before sentiment is assessed.
- Trading actions depend on the crossover, sentiment, position state, and unrealized profit or loss.
- Execution checks constrain position size and validate order quantities.
- The document describes a workflow design but provides no performance results.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.