Signal Convergence Strategy

This agent monitors four independent data sources for trading signals. When 2+ signals from different sources converge on the same ticker within 7 days, an LLM synthesizes them into a holistic trading decision.

Signal Sources

SourceDataEdgeFrequency
8-KSEC EDGAR material event filingsLLM reads filings faster than human analystsEvery 30 min
EARNINGSYahoo Finance earnings estimates vs actualsPEAD: stocks drift 30-60 days after surpriseEvery 30 min
INSIDERSEC EDGAR Form 4 insider purchases2+ officers buying = strong convictionEvery 30 min
TECHPrice, volume, RSI (Yahoo Finance)Confirms momentum — not predictive aloneEvery 30 min

Convergence Logic

Each signal fires independently into a rolling 7-day ledger. When 2+ signals from different sources appear on the same ticker, the LLM brain (Claude Sonnet) analyzes them holistically and assigns a conviction score (1-10). Only conviction ≥ 7 triggers a trade.

Position Sizing

Conviction% of PortfolioFrequency
73%Regular (good signals)
85%Strong (clear catalyst + confirmation)
97%Very strong (rare, exceptional)
1010%Maximum (once per quarter caliber)

Exit Rules

RuleTriggerAction
Hard StopPrice drops 15% below entryGTC stop order on Alpaca
Trailing StopPrice rises 12%+ above entryCancel hard stop, trail 10% below peak
Time Stop30 trading days (~42 calendar)Market sell at close

Risk Management

Max 12 concurrent positions. Max 25% in any one sector. If portfolio drops 5% in a single day, all new entries paused for 24 hours. No averaging down — ever.

LLM Brain

Uses Anthropic Claude API (undefined) with temperature 0.3. Max 100 calls/day, 24-hour result cache. Estimated cost: ~$0.50-2.00/day.