Analysis — Direction
Recomputed from btc.db on every request · 2026-11-18 15:02:07 UTC
The phase filter applies to all sections. Only evaluated UP/DOWN rows are included. Strength = max(p_up, p_down). Accuracy uses stored correct (missing values are recomputed; ties predict UP). Brier = mean((p_up − outcome)²), where UP = 1 and DOWN = 0; lower is better (50/50 baseline: 0.25). Empty groups show —. Invalid probability rows excluded: 0; correct values recomputed: 0.
Phase comparison
| Phase | Model | N | Correct | Accuracy | Brier score | Avg prediction strength |
|---|---|---|---|---|---|---|
| Phase 1 | GPT | 169 | 72 | 42.6% | 0.2601 | 54.7% |
| Phase 1 | Jev | 169 | 77 | 45.6% | 0.3851 | 79.7% |
| Phase 2 | GPT | 48 | 23 | 47.9% | 0.2553 | 55.0% |
| Phase 2 | Jev | 48 | 23 | 47.9% | 0.3386 | 76.2% |
| Phase 3 | GPT | 48 | 20 | 41.7% | 0.2683 | 57.8% |
| Phase 3 | Jev | 48 | 23 | 47.9% | 0.3569 | 77.0% |
Direction accuracy by realized volatility
Retrospective / conditional on realized volatility: subsequent-hour RV is known only afterward. This is exploratory and not tradable prospectively. Phase 4 thresholds were calibrated after the direction experiments. Observations from different models for the same hour are not independent.
RV = 100 × sqrt(sum(log(C_i / C_(i−1))²)), exactly twelve consecutive 5m returns including the preceding close. QUIET: RV < 0.227425610%; NORMAL: 0.227425610% ≤ RV < 0.370664156%; ACTIVE: RV ≥ 0.370664156%.
GPT / OpenAI: ACTIVE 34.9% (N=86), non-ACTIVE 47.8% (N=178); difference -12.9 percentage points. Jev: ACTIVE 41.9% (N=86), non-ACTIVE 48.3% (N=178); difference -6.5 percentage points.
Missing RV excluded: 2; invalid probability rows excluded: 0. ALL includes only RV-assigned rows. Stored actual_return is in percent; missing/invalid returns are excluded only from magnitude metrics (Return N). No interpolation or network fetching occurs in this page.
| Phase | Model | Eligible N | RV assigned | Missing RV |
|---|---|---|---|---|
| all | openai | 265 | 264 | 1 |
| all | jev | 265 | 264 | 1 |
| phase1 | openai | 169 | 169 | 0 |
| phase1 | jev | 169 | 169 | 0 |
| phase2 | openai | 48 | 48 | 0 |
| phase2 | jev | 48 | 48 | 0 |
| phase3 | openai | 48 | 47 | 1 |
| phase3 | jev | 48 | 47 | 1 |
| Phase | Model | Actual regime | N | Correct | Accuracy | Brier | Return N | Mean |return| | Median |return| | Mean RV |
|---|---|---|---|---|---|---|---|---|---|---|
| all | GPT / OpenAI | ALL | 264 | 115 | 43.6% | 0.2606 | 264 | 0.2488% | 0.1726% | 0.3368% |
| all | GPT / OpenAI | QUIET | 89 | 40 | 44.9% | 0.2634 | 89 | 0.1336% | 0.1142% | 0.1719% |
| all | GPT / OpenAI | NORMAL | 89 | 45 | 50.6% | 0.2486 | 89 | 0.2033% | 0.1829% | 0.2915% |
| all | GPT / OpenAI | ACTIVE | 86 | 30 | 34.9% | 0.2703 | 86 | 0.4150% | 0.3365% | 0.5542% |
| all | GPT / OpenAI | NON-ACTIVE | 178 | 85 | 47.8% | 0.2560 | 178 | 0.1685% | 0.1446% | 0.2317% |
| all | Jev | ALL | 264 | 122 | 46.2% | 0.3726 | 264 | 0.2488% | 0.1726% | 0.3368% |
| all | Jev | QUIET | 89 | 36 | 40.4% | 0.4207 | 89 | 0.1336% | 0.1142% | 0.1719% |
| all | Jev | NORMAL | 89 | 50 | 56.2% | 0.3205 | 89 | 0.2033% | 0.1829% | 0.2915% |
| all | Jev | ACTIVE | 86 | 36 | 41.9% | 0.3768 | 86 | 0.4150% | 0.3365% | 0.5542% |
| all | Jev | NON-ACTIVE | 178 | 86 | 48.3% | 0.3706 | 178 | 0.1685% | 0.1446% | 0.2317% |
| phase1 | GPT / OpenAI | ALL | 169 | 72 | 42.6% | 0.2601 | 169 | 0.2520% | 0.1787% | 0.3532% |
| phase1 | GPT / OpenAI | QUIET | 50 | 20 | 40.0% | 0.2679 | 50 | 0.1361% | 0.1094% | 0.1727% |
| phase1 | GPT / OpenAI | NORMAL | 57 | 30 | 52.6% | 0.2457 | 57 | 0.2088% | 0.1829% | 0.2947% |
| phase1 | GPT / OpenAI | ACTIVE | 62 | 22 | 35.5% | 0.2669 | 62 | 0.3853% | 0.2608% | 0.5527% |
| phase1 | GPT / OpenAI | NON-ACTIVE | 107 | 50 | 46.7% | 0.2561 | 107 | 0.1748% | 0.1460% | 0.2377% |
| phase1 | Jev | ALL | 169 | 77 | 45.6% | 0.3851 | 169 | 0.2520% | 0.1787% | 0.3532% |
| phase1 | Jev | QUIET | 50 | 19 | 38.0% | 0.4582 | 50 | 0.1361% | 0.1094% | 0.1727% |
| phase1 | Jev | NORMAL | 57 | 32 | 56.1% | 0.3273 | 57 | 0.2088% | 0.1829% | 0.2947% |
| phase1 | Jev | ACTIVE | 62 | 26 | 41.9% | 0.3794 | 62 | 0.3853% | 0.2608% | 0.5527% |
| phase1 | Jev | NON-ACTIVE | 107 | 51 | 47.7% | 0.3884 | 107 | 0.1748% | 0.1460% | 0.2377% |
| phase2 | GPT / OpenAI | ALL | 48 | 23 | 47.9% | 0.2553 | 48 | 0.1886% | 0.1550% | 0.2504% |
| phase2 | GPT / OpenAI | QUIET | 30 | 15 | 50.0% | 0.2600 | 30 | 0.1235% | 0.1270% | 0.1635% |
| phase2 | GPT / OpenAI | NORMAL | 10 | 7 | 70.0% | 0.2189 | 10 | 0.2117% | 0.2296% | 0.3022% |
| phase2 | GPT / OpenAI | ACTIVE | 8 | 1 | 12.5% | 0.2831 | 8 | 0.4039% | 0.3847% | 0.5116% |
| phase2 | GPT / OpenAI | NON-ACTIVE | 40 | 22 | 55.0% | 0.2497 | 40 | 0.1455% | 0.1465% | 0.1981% |
| phase2 | Jev | ALL | 48 | 23 | 47.9% | 0.3386 | 48 | 0.1886% | 0.1550% | 0.2504% |
| phase2 | Jev | QUIET | 30 | 12 | 40.0% | 0.3874 | 30 | 0.1235% | 0.1270% | 0.1635% |
| phase2 | Jev | NORMAL | 10 | 7 | 70.0% | 0.2312 | 10 | 0.2117% | 0.2296% | 0.3022% |
| phase2 | Jev | ACTIVE | 8 | 4 | 50.0% | 0.2896 | 8 | 0.4039% | 0.3847% | 0.5116% |
| phase2 | Jev | NON-ACTIVE | 40 | 19 | 47.5% | 0.3484 | 40 | 0.1455% | 0.1465% | 0.1981% |
| phase3 | GPT / OpenAI | ALL | 47 | 20 | 42.6% | 0.2683 | 47 | 0.2985% | 0.2033% | 0.3658% |
| phase3 | GPT / OpenAI | QUIET | 9 | 5 | 55.6% | 0.2494 | 9 | 0.1536% | 0.1301% | 0.1958% |
| phase3 | GPT / OpenAI | NORMAL | 22 | 8 | 36.4% | 0.2696 | 22 | 0.1854% | 0.1537% | 0.2784% |
| phase3 | GPT / OpenAI | ACTIVE | 16 | 7 | 43.8% | 0.2771 | 16 | 0.5353% | 0.4955% | 0.5816% |
| phase3 | GPT / OpenAI | NON-ACTIVE | 31 | 13 | 41.9% | 0.2637 | 31 | 0.1762% | 0.1308% | 0.2544% |
| phase3 | Jev | ALL | 47 | 22 | 46.8% | 0.3625 | 47 | 0.2985% | 0.2033% | 0.3658% |
| phase3 | Jev | QUIET | 9 | 5 | 55.6% | 0.3237 | 9 | 0.1536% | 0.1301% | 0.1958% |
| phase3 | Jev | NORMAL | 22 | 11 | 50.0% | 0.3435 | 22 | 0.1854% | 0.1537% | 0.2784% |
| phase3 | Jev | ACTIVE | 16 | 6 | 37.5% | 0.4104 | 16 | 0.5353% | 0.4955% | 0.5816% |
| phase3 | Jev | NON-ACTIVE | 31 | 16 | 51.6% | 0.3377 | 31 | 0.1762% | 0.1308% | 0.2544% |
Calibration analysis
Blue bar: actual accuracy. Black marker: ideal accuracy, equal to the mean prediction strength in that bucket. Buckets include their lower bound and exclude their upper bound, except 100% is included in the last bucket.
GPT
| Strength bucket | N | Accuracy | Ideal (mean strength) | Actual / ideal · 0–100% |
|---|---|---|---|---|
| 50%–55% | 129 | 43.4% | 53.0% | |
| 55%–60% | 117 | 42.7% | 56.6% | |
| 60%–70% | 19 | 47.4% | 63.2% | |
| 70%–80% | 0 | - | - | — |
| 80%–90% | 0 | - | - | — |
| 90%–100% | 0 | - | - | — |
Jev
| Strength bucket | N | Accuracy | Ideal (mean strength) | Actual / ideal · 0–100% |
|---|---|---|---|---|
| 50%–55% | 22 | 45.5% | 52.4% | |
| 55%–60% | 19 | 26.3% | 57.1% | |
| 60%–70% | 34 | 44.1% | 64.0% | |
| 70%–80% | 43 | 62.8% | 74.1% | |
| 80%–90% | 60 | 48.3% | 84.9% | |
| 90%–100% | 87 | 42.5% | 93.5% |
Threshold analysis
Keep predictions whose strength is at least the threshold (not Jev's separate confidence field). Compare accuracy and Brier together with N; higher thresholds leave fewer observations. These are historical subsets, not evidence of future trading profit.
GPT
| Minimum strength | N | Accuracy | Brier score |
|---|---|---|---|
| ≥ 50% | 265 | 43.4% | 0.2607 |
| ≥ 55% | 136 | 43.4% | 0.2661 |
| ≥ 60% | 19 | 47.4% | 0.2795 |
| ≥ 70% | 0 | - | - |
| ≥ 80% | 0 | - | - |
| ≥ 90% | 0 | - | - |
Jev
| Minimum strength | N | Accuracy | Brier score |
|---|---|---|---|
| ≥ 50% | 265 | 46.4% | 0.3716 |
| ≥ 55% | 243 | 46.5% | 0.3822 |
| ≥ 60% | 224 | 48.2% | 0.3906 |
| ≥ 70% | 190 | 48.9% | 0.4089 |
| ≥ 80% | 147 | 44.9% | 0.4586 |
| ≥ 90% | 87 | 42.5% | 0.5066 |
Jev confidence investigation
Probability margin = abs(p_up − p_down). Evaluated Jev rows with valid confidence only. Missing or invalid confidence excluded: 0.
If confidence repeats the probability margin, r approaches 1 and the absolute difference approaches 0. The table groups pairs by margin (lower bound included; 100% included in the last group).
| Probability margin | N | Mean margin | Mean Jev confidence |
|---|---|---|---|
| 0–10% | 22 | 4.8% | 4.8% |
| 10–20% | 22 | 14.9% | 14.9% |
| 20–30% | 18 | 24.9% | 24.8% |
| 30–40% | 19 | 35.9% | 35.8% |
| 40–50% | 16 | 45.0% | 45.2% |
| 50–60% | 21 | 52.9% | 52.8% |
| 60–70% | 27 | 64.1% | 64.1% |
| 70–80% | 33 | 74.5% | 74.5% |
| 80–90% | 69 | 85.3% | 85.4% |
| 90–100% | 18 | 93.1% | 92.9% |
BTC Predictor