Automating Social-Media Signals for Stock Perpetual Futures

Summary

This article outlines a system that turns an analyst’s posts on X into potential trades in US equity perpetual futures. It proposes collecting posts through an RSS feed, asking a language model to identify explicitly named tickers and classify direction and confidence, then matching those tickers to available contracts. The prompt is tailored to distinguish genuine views from teaser questions and broad commentary. The proposed controls include limited position sizes, a cap on concurrent holdings, drawdown-based exits, a dashboard, and a notify-only mode for observing signals before enabling orders.

The author presents the influencer’s stock-picking record and the system’s signal interpretation as reasons for the approach, but supplies no independently verifiable strategy-level performance results. The article also notes that perpetual contracts do not confer stock ownership or dividends and carry funding costs. The stop-loss section is blank and the trailing-exit code is truncated, so key risk rules cannot be fully assessed. Social posts and language-model classifications can be wrong, and results depend heavily on source quality and execution.

Key ideas

• The proposed pipeline collects social posts, extracts ticker-level direction with a language model, and routes signals to matching perpetual contracts.
• Prompt guidance is used to filter teaser questions and distinguish specific ticker views from general commentary.
• Notify-only operation is proposed as a way to review classifications before allowing automated trades.
• Position limits and drawdown-based exits are intended to constrain exposure while allowing profitable trades room to develop.
• The article provides no verifiable strategy performance, and its stop-loss description and trailing-exit implementation are incomplete.

Tags

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