Back to Browse
x402-factory Edge Signal Backtest
x402
x402-factory Edge Signal Backtest is a paid API for AI agents from x402-factory.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-13).
Returns historical performance metrics for the edge signal model: hit rate, average edge captured, calibration curve, and per-hazard breakdowns over resolved markets.
Price / call$0.05
Success—
StatusUnknown
How this service works
Historical performance of the edge signal: hit rate, calibration, by hazard — Aggregates stored edge signals whose markets have resolved: how often the model beat the market (hit rate), average absolute-error improvement (edge captured), a model calibration curve, and per-hazard breakdowns. model_label is explicit about which model produced the signals.
Output
Returns a JSON object with: total number of resolved signals, overall hit rate (0-1), average absolute-error improvement (avg_edge_captured), an array of calibration curve buckets (predicted vs realized probabilities), per-hazard breakdown (hazard name, count, hit rate), and the model_label identifying which model produced the signals.
Example use cases
Example prompt
“Show me the backtest performance of the edge signal model over the last 90 days — I want to see the hit rate, average edge captured, and the calibration curve broken down by hazard.”
Technical details
Endpoint
GEThttps://x402-factory.com/v1/edge/backtestWhen to prefer
Use this endpoint when you need to evaluate the historical accuracy and calibration of the edge signal model over resolved prediction markets — especially for model validation, backtesting a trading strategy, or auditing whether the model's predicted probabilities match realized outcomes. Prefer this over live signal endpoints when the goal is retrospective performance analysis rather than actionable current signals.
Side effects
- Invalid window parameter (out of integer range) returns validation error
- min_divergence outside 0-1 range returns validation error
- No resolved signals in the requested window returns empty or zero-count result
- Payment failure (x402 protocol) blocks access if USDC payment not processed
- Service unavailable returns 5xx error
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| inputrequired | object | |
| output | object |
Output
Schema · Response
{
"type": "json",
"example": {
"data": {
"hit_rate": 0.525,
"by_hazard": [
{
"n": 39,
"hazard": "precip_above",
"hit_rate": 0.487
},
{
"n": 31,
"hazard": "temp_above",
"hit_rate": 0.452
},
{
"n": 31,
"hazard": "any_precip",
"hit_rate": 0.548
},
{
"n": 30,
"hazard": "wind_above",
"hit_rate": 0.7
},
{
"n": 29,
"hazard": "named_storm_landfall",
"hit_rate": 0.448
}
],
"n_signals": 160,
"model_label": "stub-model",
"avg_edge_captured": 0.0044,
"calibration_curve": [
{
"bucket": "0.0–0.1",
"realized": 0,
"predicted": 0.068
},
{
"bucket": "0.1–0.2",
"realized": 0.333,
"predicted": 0.148
},
{
"bucket": "0.2–0.3",
"realized": 0.462,
"predicted": 0.254
},
{
"bucket": "0.3–0.4",
"realized": 0.316,
"predicted": 0.348
},
{
"bucket": "0.4–0.5",
"realized": 0.667,
"predicted": 0.431
},
{
"bucket": "0.5–0.6",
"realized": 0.474,
"predicted": 0.541
},
{
"bucket": "0.6–0.7",
"realized": 0.583,
"predicted": 0.644
},
{
"bucket": "0.7–0.8",
"realized": 0.737,
"predicted": 0.75
},
{
"bucket": "0.8–0.9",
"realized": 0.889,
"predicted": 0.842
},
{
"bucket": "0.9–1.0",
"realized": 0.75,
"predicted": 0.953
}
]
},
"meta": {
"docs": "https://x402-factory.com/docs/edge.backtest",
"sources": [
"stub-model",
"kalshi",
"polymarket"
],
"version": "1.0.0",
"endpoint": "/v1/edge/backtest",
"data_mode": "live",
"freshness": "daily",
"request_id": "req_00000000",
"generated_at": "2026-08-21T03:58:57.921Z"
}
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"