# sector classification

Markets are automatically classified into 8 sectors based on keyword matching against the market question text.

## The 8 Sectors

### Politics

```
election, president, congress, vote, democrat, republican, trump, biden,
senate, governor, parliament, minister, party, nomination, inauguration,
impeach, legislation, ballot, poll, primary, caucus, electoral
```

### Crypto

```
bitcoin, ethereum, crypto, token, blockchain, defi, nft, btc, eth,
solana, dogecoin, altcoin, mining, halving, stablecoin, web3
```

### Sports

```
nba, nfl, mlb, nhl, soccer, football, basketball, baseball,
championship, game, match, tournament, playoff, finals, mvp,
super bowl, world cup, olympics, league, draft, trade
```

### Economy

```
fed, inflation, gdp, rates, recession, jobs, unemployment, stock,
market, interest, treasury, debt, trade, tariff, cpi, fomc,
dow, nasdaq, s&p, earnings, ipo
```

### Geopolitics

```
war, ukraine, russia, china, nato, sanctions, conflict, treaty,
invasion, ceasefire, nuclear, missile, alliance, territory,
border, military, diplomacy, un, security council
```

### Tech / AI

```
ai, openai, google, apple, microsoft, spacex, launch, tech,
chatgpt, claude, gemini, llm, robot, autonomous, startup,
acquisition, agi, silicon valley, elon
```

### Culture

```
oscar, grammy, emmy, movie, album, celebrity, viral, award,
tiktok, streaming, netflix, box office, concert, festival,
fashion, influencer, scandal, reality tv
```

### Science

```
climate, vaccine, fda, space, discovery, research, study,
nasa, mars, asteroid, drug, trial, approval, pandemic,
outbreak, species, quantum, fusion, genome
```

## Classification Logic

1. Market question text is lowercased
2. Each sector's keywords are tested as regex patterns
3. The first matching sector wins
4. If no keywords match, the market is classified as "Other"

Sectors are checked in a fixed order: Politics, Crypto, Sports, Economy, Geopolitics, Tech, Culture, Science. This means a market about "Trump's Bitcoin policy" would match Politics (checked first) rather than Crypto.

## Where Classification Is Used

| Location             | Purpose                                    |
| -------------------- | ------------------------------------------ |
| **Markets table**    | Sector badge on each row                   |
| **Sectors panel**    | Aggregate barometers                       |
| **MCP get\_markets** | `sector` filter parameter                  |
| **AI analysis**      | Sector-specific prompts and search queries |
| **Agent system**     | Market filtering for trading universe      |

## Limitations

* Keyword matching is imperfect. A market about "election betting" would match Politics even if it's really about the prediction market industry.
* Multi-sector markets (e.g., "Will the EU regulate AI?") match the first sector only.
* New topics may not match any sector until keywords are updated.
* Generic words in some sectors (like "game" in Sports) can cause false positives.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://yesno-1.gitbook.io/yesno-docs/methodology/sector-classification.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.