Entity Correlation and Extraction

Part of the Signal Intelligence guide, which indexes every topic.

Entity-Aware Correlation

The signal engine uses a registry-backed entity knowledge base to intelligently correlate market movements with news coverage. Rather than simple keyword matching, the system understands that “AVGO” (the ticker) relates to “Broadcom” (the company), “AI chips” (the sector), and entities like “Nvidia” (a competitor).

Entity Knowledge Base

Each entity in the registry contains:

Field	Purpose	Example
ID	Canonical identifier	`broadcom`
Name	Display name	`Broadcom Inc.`
Type	Category	`company`, `commodity`, `crypto`, `country`, `person`
Aliases	Alternative names	`AVGO`, `Broadcom`, `Broadcom Inc`
Keywords	Related topics	`AI chips`, `semiconductors`, `VMware`
Sector	Industry classification	`semiconductors`
Related	Linked entities	`nvidia`, `intel`, `amd`

Entity Types

Type	Count	Examples
Companies	38	Nvidia, Apple, Tesla, Broadcom, Boeing, Lockheed Martin, TSMC, Rheinmetall
Indices	3	S&P 500, Dow Jones, NASDAQ
Sectors	5	Technology (XLK), Finance (XLF), Energy (XLE), Healthcare (XLV), Semiconductors (SMH)
Commodities	6	Oil (WTI), Gold, Natural Gas, Copper, Silver, VIX
Crypto	3	Bitcoin, Ethereum, Solana
Countries	11	China, Russia, Iran, Israel, Ukraine, Taiwan, Saudi Arabia, UAE, Qatar, Turkey, Egypt

How Entity Matching Works

When a market moves significantly (≥2%), the system:

Looks up the ticker in the entity registry (e.g., AVGO → broadcom)
Gathers all identifiers: aliases, keywords, sector peers, related entities
Scans all news clusters for matches against any identifier
Scores confidence based on match type:
- Alias match (exact name): 95%
- Keyword match (topic): 70%
- Related entity match: 60%

If correlated news is found → “Market Move Explained” signal with the news headline. If no correlation after exhaustive search → “Silent Divergence” signal.

Example: Broadcom +2.5%

Ticker AVGO detected with +2.5% move
Entity lookup: broadcom
Search terms: ["Broadcom", "AVGO", "AI chips", "semiconductors", "VMware", "nvidia", "intel", "amd"]
News scan finds: "Broadcom AI Revenue Beats Estimates"
Result: "✓ Market Move Explained: Broadcom AI Revenue Beats Estimates"

Without this system, the same move would generate a generic “Silent Divergence: AVGO +2.5%” signal.

Sector Coverage

The entity registry spans strategically significant sectors:

Sector	Examples	Keywords Tracked
Technology	Apple, Microsoft, Nvidia, Google, Meta, TSMC	AI, cloud, chips, datacenter, streaming
Defense & Aerospace	Lockheed Martin, Raytheon, Northrop Grumman, Boeing, Rheinmetall, Airbus	F-35, missiles, drones, tanks, defense contracts
Semiconductors	ASML, Samsung, AMD, Intel, Broadcom	Lithography, EUV, foundry, fab, wafer
Critical Minerals	Albemarle, SQM, MP Materials, Freeport-McMoRan	Lithium, rare earth, cobalt, copper
Finance	JPMorgan, Berkshire Hathaway, Visa, Mastercard	Banking, credit, investment, interest rates
Healthcare	Eli Lilly, Novo Nordisk, UnitedHealth, J&J	Pharma, drugs, GLP-1, obesity, diabetes
Energy	Exxon, Chevron, ConocoPhillips	Oil, gas, drilling, refinery, LNG
Consumer	Tesla, Walmart, Costco, Home Depot	EV, retail, grocery, housing

This broad coverage enables correlation detection across diverse geopolitical and market events.

Entity Registry Architecture

The entity registry is a knowledge base with rich metadata for intelligent correlation:

{
  id: 'NVDA',           // Unique identifier
  name: 'Nvidia',       // Display name
  type: 'company',      // company | country | index | commodity | currency
  sector: 'semiconductors',
  searchTerms: ['Nvidia', 'NVDA', 'Jensen Huang', 'H100', 'CUDA'],
  aliases: ['nvidia', 'nvda'],
  competitors: ['AMD', 'INTC'],
  related: ['AVGO', 'TSM', 'ASML'],  // Related entities
  country: 'US',        // Headquarters/origin
}

Entity Types:

Type	Count	Use Case
`company`	38	Market-news correlation, sector analysis
`country`	11	Focal point detection, CII scoring
`index`	3	Market overview, regional tracking
`commodity`	6	Energy and mineral correlation
`sector`	5	Sector cascade analysis
`crypto`	3	Cryptocurrency correlation

Lookup Indexes: The registry provides multiple lookup paths for fast entity resolution:

Index	Query Example	Use Case
`byId`	`'NVDA'` → Nvidia entity	Direct lookup from ticker
`byAlias`	`'nvidia'` → Nvidia entity	Case-insensitive name match
`byKeyword`	`'AI chips'` → [Nvidia, AMD, Intel]	News keyword extraction
`bySector`	`'semiconductors'` → all chip companies	Sector cascade analysis
`byCountry`	`'US'` → all US entities	Country-level aggregation

Entity Extraction System

The dashboard extracts named entities (companies, countries, leaders, organizations) from news headlines to enable news-to-market correlation and entity-based filtering.

How It Works

Headlines are scanned against a curated entity index containing:

Entity Type	Examples	Purpose
Companies	Apple, Tesla, NVIDIA, Boeing	Market symbol correlation
Countries	Russia, China, Iran, Ukraine	Geopolitical attribution
Leaders	Putin, Xi Jinping, Khamenei	Political event tracking
Organizations	NATO, OPEC, Fed, SEC	Institutional news filtering
Commodities	Oil, Gold, Bitcoin	Commodity news correlation

Entity Matching

Each entity has multiple match patterns for comprehensive detection:

Entity: NVIDIA (NVDA)
  Aliases: nvidia, nvda, jensen huang
  Keywords: gpu, h100, a100, cuda, ai chip
  Match Types:
    - Name match: "NVIDIA announces..." → 95% confidence
    - Alias match: "Jensen Huang says..." → 90% confidence
    - Keyword match: "H100 shortage..." → 70% confidence

Confidence Scoring

Entity extraction produces confidence scores based on match quality:

Match Type	Confidence	Example
Direct name	95%	“Apple reports earnings”
Alias	90%	“Tim Cook announces…”
Keyword	70%	“iPhone sales decline”
Related cluster	63%	Secondary headline mention (90% × 0.7)

Market Correlation

When a market symbol moves significantly, the system searches news clusters for related entities:

Symbol lookup - Find entity by market symbol (e.g., AAPL → Apple)
News search - Find clusters mentioning the entity or related entities
Confidence ranking - Sort by extraction confidence
Result - “Market Move Explained” or “Silent Divergence” signal

This enables signals like:

Explained: “AVGO +5.2% — Broadcom mentioned across news clusters (AI chip demand)”
Silent: “AVGO +5.2% — No correlated news after entity search”

Intelligence & Analysis

Map Layers

Finance

Entity Correlation and Extraction

Entity-Aware Correlation

Entity Knowledge Base

Entity Types

How Entity Matching Works

Example: Broadcom +2.5%

Sector Coverage

Entity Registry Architecture

Entity Extraction System

How It Works

Entity Matching

Confidence Scoring

Market Correlation

​Entity-Aware Correlation

​Entity Knowledge Base

​Entity Types

​How Entity Matching Works

​Example: Broadcom +2.5%

​Sector Coverage

​Entity Registry Architecture

​Entity Extraction System

​How It Works

​Entity Matching

​Confidence Scoring

​Market Correlation

Entity-Aware Correlation

Entity Knowledge Base

Entity Types

How Entity Matching Works

Example: Broadcom +2.5%

Sector Coverage

Entity Registry Architecture

Entity Extraction System

How It Works

Entity Matching

Confidence Scoring

Market Correlation