# Metaculus Forecast Tracker (`gochujang/metaculus-forecasts`) Actor

Fetch prediction questions and community forecasts from Metaculus — the rigorous research-grade forecasting platform. AI, pandemics, geopolitics, science, and more. No API key required.

- **URL**: https://apify.com/gochujang/metaculus-forecasts.md
- **Developed by:** [Hojun Lee](https://apify.com/gochujang) (community)
- **Categories:** Business
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.00 / 1,000 item processeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

### Metaculus Forecast Tracker — Research-Grade Prediction Markets

Fetch prediction questions and community forecasts from **Metaculus**, the rigorous scientific forecasting platform trusted by researchers, governments, and policy analysts. Track what the crowd thinks will happen in AI, geopolitics, pandemics, economics, science, and more — with calibration data, forecaster counts, and resolution criteria. No API key required.

Metaculus is not play money — it's used by the CDC, IARPA, and major research institutions to aggregate expert and crowd forecasts on consequential questions.

### What You Get

For each question, the actor returns:

- **Title, description, resolution criteria**
- **Community prediction %** — the crowd's median probability
- **Forecaster count** — number of people who made predictions
- **Forecast count** — total number of individual forecasts made
- **Status** — open, resolved, or closed
- **Resolution** — YES/NO/value when resolved, with percentage for binary questions
- **Categories and tags** — topic classification
- **Dates** — created, open, close, resolved
- **Direct URL** to the question on Metaculus

### Modes

| Mode | Description |
|------|-------------|
| `search` | Keyword search across all questions |
| `recent` | Most recently opened questions |
| `closing_soon` | Open questions ordered by close date |
| `specific` | Fetch by exact question ID(s) |

### Input Parameters

| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `mode` | string | `"search"` | See modes table |
| `query` | string | — | Keyword search (e.g. `"AGI"`, `"election"`, `"pandemic"`) |
| `category` | string | — | Category slug: `"artificial-intelligence"`, `"geopolitics"`, etc. |
| `status` | string | `"open"` | Filter: `"open"`, `"resolved"`, `"all"` |
| `orderBy` | string | `"-activity"` | Sort order |
| `limit` | integer | `30` | Max questions (max 500) |
| `questionIds` | array | `[]` | Specific question IDs for direct lookup |

### Sample Output

```json
{
  "id": 14798,
  "title": "Will GPT-5 be released before January 1, 2026?",
  "url": "https://www.metaculus.com/questions/14798/",
  "question_type": "binary",
  "resolution_criteria": "Resolves YES if OpenAI officially releases a model named GPT-5...",
  "description": "OpenAI has been developing its next flagship language model...",
  "community_prediction_pct": 72.4,
  "forecaster_count": 1847,
  "forecast_count": 8320,
  "vote_score": 241,
  "status": "resolved",
  "is_resolved": true,
  "resolution_value": 100.0,
  "resolution_text": "YES",
  "categories": ["Artificial Intelligence"],
  "tags": ["openai", "gpt", "language-models"],
  "created_at": "2024-03-01T09:00:00Z",
  "close_at": "2025-12-31T23:59:00Z",
  "resolved_at": "2025-08-15T14:22:00Z",
  "fetched_at": "2025-01-15T12:00:00Z"
}
```

### Popular Category Slugs

| Slug | Topic |
|------|-------|
| `artificial-intelligence` | AI, ML, AGI, LLMs |
| `geopolitics` | International relations, conflicts |
| `covid-19` | Pandemic, vaccines, variants |
| `economics` | Recession, inflation, markets |
| `science` | Research breakthroughs |
| `technology` | Tech products, releases |
| `united-states` | US politics and policy |
| `climate` | Climate change, energy |

### Use Cases

- **Research aggregation** — pull expert consensus on AI timelines, pandemic risks, geopolitical events
- **Policy analysis** — what does the forecasting community think about regulatory outcomes?
- **Calibration datasets** — build datasets of predictions vs. resolutions for ML training
- **AI safety research** — track community forecasts on AI progress milestones
- **Trend detection** — which categories are generating the most forecasting activity?
- **Academic research** — study prediction market accuracy and forecaster behavior

### About Metaculus

Metaculus was founded in 2015 and has resolved over 15,000 questions, making it one of the most calibrated prediction platforms in existence. Unlike Polymarket or Manifold, Metaculus focuses on epistemically rigorous questions with clear resolution criteria — making it particularly valuable for academic and research use cases.

### Pricing

Pay-per-event: **$0.001 per question returned** (~$0.03 for 30 questions, $0.50 for 500).

### FAQ

**Is Metaculus real money?**
No — Metaculus uses points, not real money. Users earn points for accurate forecasts, which builds a track record of calibration.

**How calibrated are Metaculus forecasts?**
Very well calibrated on average. Questions with 80%+ community prediction resolve YES about 80% of the time. Independent research has confirmed strong calibration across thousands of resolved questions.

**Can I get historical forecast data?**
Yes — the `status: "resolved"` filter returns resolved questions with their `resolution_value` and `community_prediction_pct`, enabling calibration analysis.

**How often is the data updated?**
Community predictions update continuously as forecasters submit new predictions. For monitoring active questions, schedule the actor to run daily or hourly.

***

### Related actors

- [AI Model Tracker](https://apify.com/gochujang/openai-model-tracker) — AI model releases to cross-reference with Metaculus AI timeline forecasts
- [Tech News Aggregator](https://apify.com/gochujang/tech-news-aggregator) — News coverage to correlate with shifts in Metaculus community prediction %
- [Crypto Regulation Tracker](https://apify.com/gochujang/crypto-regulation-tracker) — Regulatory event data for cross-referencing crypto policy forecasts

### Feedback

If this actor powers your research, a review helps others find it: [Leave a review on Apify Store](https://apify.com/gochujang/metaculus-forecasts#reviews)

***

**Keywords:** Metaculus forecast tracker, prediction market research, AI timeline forecasts, geopolitics probability, pandemic prediction data, science forecasting platform, expert crowd forecasts, calibrated predictions, community forecast API, Metaculus questions scraper, AI existential risk forecasts, crypto regulation probability, research forecasting data

# Actor input Schema

## `mode` (type: `string`):

How to find questions: 'search' by keyword, 'recent' for newest, 'closing\_soon' for questions closing soon, 'specific' for exact question IDs.

## `query` (type: `string`):

Keyword to search for (e.g. 'AI', 'pandemic', 'election', 'nuclear').

## `category` (type: `string`):

Filter by category slug (e.g. 'artificial-intelligence', 'geopolitics', 'science', 'economics', 'covid-19').

## `status` (type: `string`):

Filter by question status.

## `orderBy` (type: `string`):

How to sort results.

## `limit` (type: `integer`):

Maximum questions to return (max 500).

## `questionIds` (type: `array`):

Specific Metaculus question IDs to fetch (for 'specific' mode).

## Actor input object example

```json
{
  "mode": "search",
  "status": "open",
  "orderBy": "-activity",
  "limit": 30,
  "questionIds": []
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("gochujang/metaculus-forecasts").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("gochujang/metaculus-forecasts").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call gochujang/metaculus-forecasts --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,gochujang/metaculus-forecasts"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/BMUMN2lUpCrPPgpTr/builds/qmWScJq8YRvAGvBFq/openapi.json