How Silicon Analysis Ranks AI & Semiconductor Companies

Live scores blend real-time news analysis, price momentum, fundamentals, and data confidence metrics. All calculations are deterministic and explainable.

v3.0

Alpha Score (Quantamental)

Alpha v3 is a quantamental signal combining technical momentum, news sentiment, and fundamentals. It uses risk-adjusted returns, evidence-gated news, and valuation circuit breakers to identify quality opportunities.

35%

News Signal

Aggregated news impact, sentiment, and severity from the Intel Wire.

30%

Risk-Adjusted Momentum

20-day risk-adjusted returns, category-relative.

20%

Fundamentals (FSI)

Financial Strength Index from SEC filings.

15%

Data Confidence

Data completeness and freshness factor.

Valuation Circuit Breaker

Companies in the top 25% of P/S ratio (category-relative) receive a 0-20 point penalty. Companies with FCF yield >5% and reasonable valuations receive up to 10 bonus points. This prevents chasing momentum into extreme valuations.

Divergence Signal

Divergence measures how Alpha movement differs from price movement over 24 hours. Range: -100 to 100.

Positive Divergence (Signal Lead)

Alpha is rising faster than price. May indicate undervaluation — news and fundamentals ahead of market pricing.

Negative Divergence (Froth Risk)

Price is rising faster than Alpha. May indicate overvaluation — market pricing ahead of fundamentals.

Alert Thresholds

Automated alerts trigger when these conditions are met:

Rank Jump: 3+ position change
Alpha Spike: 10+ point change in 24h
Critical News: CRITICAL or BREAKING news detected
Divergence Alert: 20+ point divergence

Intel Wire Severity

CRITICAL: Near-term risk or major execution shifts requiring immediate attention
BREAKING: Time-sensitive news with potential market impact
CONFIRMED: Validated disclosures from official sources
ANALYSIS: Human or LLM context on strategic impact
RUMOR: Unverified information with lower reliability

Data Sources

News: NewsAPI, GNews (updated every 15 minutes)
Prices: Finnhub (primary), AlphaVantage (fallback)
Financials: SEC EDGAR

Technical Notes

All scoring uses deterministic math — no LLM in the scoring path.
Price data is cached; no external API calls on page loads.
Score recalculation runs every 15 minutes via background agents.
Model version tracked per snapshot (currently alpha_v3.0).