Market
Prices refresh every 3 seconds. Screening and evaluations, every 15.
System
Serving crypto_direction_h15 v202608131548. Decisions are counted from rows the predictor wrote — a process that is running but deciding nothing shows as zero here rather than as healthy.
Performance
Live feeds
25 instruments| Instrument | Last | 1h | High | Low | Bars | Age |
|---|---|---|---|---|---|---|
| EUR/JPY (ECN) forex | 179.1050 | -0.05% | 179.1610 | 179.1050 | 0 | 523h |
| USD/JPY (ECN) forex | 157.2270 | -0.02% | 157.2950 | 157.2260 | 0 | 523h |
| USD/CHF (ECN) forex | 0.8283 | -0.02% | 0.8284 | 0.8283 | 0 | 523h |
| USD/CAD (ECN) forex | 1.4137 | -0.05% | 1.4140 | 1.4137 | 0 | 523h |
| NZD/USD (ECN) forex | 0.5661 | -0.08% | 0.5663 | 0.5661 | 0 | 523h |
| GBP/USD (ECN) forex | 1.3242 | -0.05% | 1.3245 | 1.3240 | 0 | 523h |
| GBP/JPY (ECN) forex | 208.2960 | -0.03% | 208.3500 | 208.2720 | 0 | 523h |
| EUR/USD (ECN) forex | 1.1390 | -0.04% | 1.1391 | 1.1390 | 0 | 523h |
| AUD/USD (ECN) forex | 0.7022 | -0.05% | 0.7024 | 0.7020 | 0 | 523h |
| AVAXUSDT crypto | 7.2760 | +0.62% | 7.2760 | 7.2760 | 0 | 1119h |
| BTCUSDT crypto | 78,819.24 | +0.33% | 78,819.24 | 78,819.24 | 0 | 1119h |
| ETHUSDT crypto | 2,476.14 | +0.45% | 2,476.14 | 2,475.1 | 0 | 1119h |
| SOLUSDT crypto | 103.4300 | +0.28% | 103.4300 | 103.4200 | 0 | 1119h |
| BNBUSDT crypto | 693.4800 | +0.38% | 693.6700 | 693.4800 | 0 | 1119h |
| XRPUSDT crypto | 1.3871 | +0.53% | 1.3871 | 1.3858 | 0 | 1119h |
| ADAUSDT crypto | 0.1996 | +0.57% | 0.1996 | 0.1996 | 0 | 1119h |
| DOGEUSDT crypto | 0.08311 | +0.24% | 0.08311 | 0.08311 | 0 | 1119h |
| AUD/CAD OTC forex | 1.0435 | -0.08% | 1.0437 | 1.0430 | 0 | 1579h |
| XAU/USD OTC metal | 4,359.61 | +0.01% | 4,359.61 | 4,359.59 | 0 | 1579h |
| XAU/USD (broker feed) metal | 4,415.45 | +0.23% | 4,415.59 | 4,414.95 | 0 | 1579h |
| GBP/USD OTC forex | 1.3533 | +0.10% | 1.3539 | 1.3532 | 0 | 1579h |
| GBP/USD (broker feed) forex | 1.3490 | -0.02% | 1.3491 | 1.3490 | 0 | 1579h |
| EUR/USD OTC forex | 1.1682 | -0.04% | 1.1683 | 1.1681 | 0 | 1579h |
| EUR/USD (broker feed) forex | 1.1523 | -0.01% | 1.1523 | 1.1523 | 0 | 1579h |
| BTC/USD (broker feed) crypto | 63,374.4 | -0.21% | 63,394.24 | 63,372.2 | 0 | 1579h |
How we know — the measurements behind every claim here
Not established. One result clears on paper; none survive being counted honestly.
Best hit rate across 16 evaluations was 51.11%, against a 54.05% breakeven at an 85% payout. Below that line every trade loses money on average.
None of the 6 evaluations measured against a one-line rule beat it — always-up, momentum, or bet-against-the-last-bar, on the same rows. Whatever the models found is reproduced by betting against the previous bar, which is the bid-ask bounce rather than the market, and it is not capturable: that reversion sits inside the spread you cross to open the position.
1 of 16 clears breakeven on the raw trade count, and 0 still does once overlapping trades are counted once. A 15-minute call entered at 10:00 and another at 10:01 share fourteen of their fifteen minutes; they are not two independent pieces of evidence.
Gradient boosting on 40 indicator features
| Instrument | Expiry | Measured on | Hit rate | 95% low | Needs | One-line rule | Beats it | Samples |
|---|---|---|---|---|---|---|---|---|
| EUR/USD (ECN) | 1m | fresh | 51.11% | — | 54.05% | 51.15% | no | 101k |
| EUR/USD (ECN) | 1m | all bars | 51.96% | — | 54.05% | — | — | 148k |
| EUR/USD (ECN) | 5m | fresh | 50.14% | — | 54.05% | 50.52% | no | 105k |
| EUR/USD (ECN) | 5m | all bars | 50.77% | — | 54.05% | — | — | 154k |
| EUR/USD (ECN) | 15m | fresh | 50.14% | — | 54.05% | 50.45% | no | 106k |
| EUR/USD (ECN) | 15m | all bars | 50.91% | — | 54.05% | — | — | 156k |
| GBP/USD (ECN) | 1m | fresh | 50.88% | — | 54.05% | 51.12% | no | 85k |
| GBP/USD (ECN) | 1m | all bars | 51.52% | — | 54.05% | — | — | 155k |
| GBP/USD (ECN) | 5m | fresh | 50.36% | — | 54.05% | 50.64% | no | 88k |
| GBP/USD (ECN) | 5m | all bars | 50.86% | — | 54.05% | — | — | 161k |
| GBP/USD (ECN) | 15m | fresh | 50.16% | — | 54.05% | 50.33% | no | 88k |
| GBP/USD (ECN) | 15m | all bars | 50.32% | — | 54.05% | — | — | 163k |
Sequence model (TCN + transformer)
| Instrument | Expiry | Measured on | Hit rate | 95% low | Needs | One-line rule | Beats it | Samples |
|---|---|---|---|---|---|---|---|---|
| pooled | 1m | all bars | 51.15% | — | 54.05% | — | — | 55k |
| pooled | 5m | all bars | 51.19% | — | 54.05% | — | — | 119k |
| pooled | 15m | all bars | 51.42% | — | 54.05% | — | — | 137k |
Model A + Model B meta-labelling gate
| Instrument | Expiry | Measured on | Hit rate | 95% low | Needs | One-line rule | Beats it | Samples |
|---|---|---|---|---|---|---|---|---|
| pooled | pooled | all bars | 56.64% | 52.52% | 54.05% | — | — | 3k → 564 |
fresh counts only bars whose recent quotes were moving; all bars includes stale ones, where a quote catching up looks like a prediction. pooled means the run mixed expiries or instruments and cannot honestly be split. Where samples read 3k → 564, the second number is how many independent observations remain after overlap — the confidence bound uses that one.