Accuracy Candles — Per-Timeframe Performance Audit
The /accuracy/candles endpoint returns per-timeframe candle-level audit metrics — MAPE (mean absolute percentage error) and MAE (mean absolute error) broken down by 5m, 15m, 1h, 4h, and 1d. Computed from 47,000+ audited candles, it shows exactly which timeframes the Kronos model predicts best. Filter by ?symbol to drill into a single asset.
Endpoint
GET /api/feeds/kronos/accuracy/candles?symbol=btc_usdtParameters
| Param | Type | Required | Description |
|---|---|---|---|
symbol | query | No | Filter to a single asset, e.g. btc_usdt, eth_usdt |
limit | query | No | Cap number of candle audit records returned |
Pricing
$0.005 per request (payment after delivery — settled only if the response is successfully sent).
Example request
curl -H "X-PAYMENT: <x402-payment-header>" \
"https://kronos.seshat.markets/api/feeds/kronos/accuracy/candles?symbol=btc_usdt"Example response (truncated)
{
"symbol": "btc_usdt",
"total_candles_audited": 47213,
"by_timeframe": {
"5m": {
"mape": 0.0089,
"mae": 598.42,
"candles": 12480
},
"15m": {
"mape": 0.0121,
"mae": 812.17,
"candles": 9360
},
"1h": {
"mape": 0.0183,
"mae": 1230.55,
"candles": 11232
},
"4h": {
"mape": 0.0247,
"mae": 1665.90,
"candles": 7488
},
"1d": {
"mape": 0.0312,
"mae": 2104.33,
"candles": 6653
}
}
}Use cases
Timeframe Selection
Identify which timeframes the model predicts best for each asset. If 1h has the lowest MAPE but 4h has the highest, weight your trading strategy toward 1h signals for that symbol.
Model Risk Assessment
Before acting on a prediction, check the candle-level error for that timeframe. A high MAPE on 5m means short-term signals are noisy — adjust your confidence accordingly.
Per-Symbol Calibration
Compare MAPE across BTC, ETH, SOL, and XRP. Some assets are inherently harder to forecast — use the per-symbol breakdown to set asset-specific trust thresholds.
Strategy Backtesting
Feed MAPE/MAE into your backtest as a confidence weight per timeframe. Strategies that only trade on high-accuracy timeframes consistently outperform uniform weighting.
Frequently asked questions
What is a per-timeframe crypto forecast accuracy API?
How do I know which crypto timeframe is most predictable?
GET /api/feeds/kronos/accuracy/candles?symbol=btc_usdt and compare MAPE across timeframes. The timeframe with the lowest MAPE is where the model performs best — weight your trading strategy toward that horizon.