Rolling-origin backtest เทียบ random baseline
แต่ละงวดใช้เฉพาะข้อมูลก่อนงวดเป้าหมาย สร้าง ranking แล้วตรวจผลจริงงวดถัดไป เพื่อลด look-ahead leakage
User-defined backtest
| Strategy | Top K | Evaluated draws | Hits | Hit rate | Random baseline | Lift | 95% CI | สรุป |
|---|---|---|---|---|---|---|---|---|
| Strategyhot-20 | Top K5 | Evaluated draws450 | Hits19 | Hit rate4.22% | Random baseline5.00% | Lift-0.78% | 95% CI2.72% ถึง 6.50% | สรุปNo clear evidence of edge over random baseline. |
| Strategyhot-50 | Top K5 | Evaluated draws450 | Hits21 | Hit rate4.67% | Random baseline5.00% | Lift-0.33% | 95% CI3.07% ถึง 7.03% | สรุปNo clear evidence of edge over random baseline. |
| Strategyhot-100 | Top K5 | Evaluated draws450 | Hits20 | Hit rate4.44% | Random baseline5.00% | Lift-0.56% | 95% CI2.90% ถึง 6.76% | สรุปNo clear evidence of edge over random baseline. |
| Strategycold | Top K5 | Evaluated draws450 | Hits12 | Hit rate2.67% | Random baseline5.00% | Lift-2.33% | 95% CI1.53% ถึง 4.60% | สรุปObserved historical result was below random baseline. |
| Strategyall-time-frequency | Top K5 | Evaluated draws450 | Hits24 | Hit rate5.33% | Random baseline5.00% | Lift0.33% | 95% CI3.61% ถึง 7.81% | สรุปNo clear evidence of edge over random baseline. |
| Strategybalanced | Top K5 | Evaluated draws450 | Hits23 | Hit rate5.11% | Random baseline5.00% | Lift0.11% | 95% CI3.43% ถึง 7.55% | สรุปNo clear evidence of edge over random baseline. |
| Strategydigit-position | Top K5 | Evaluated draws450 | Hits25 | Hit rate5.56% | Random baseline5.00% | Lift0.56% | 95% CI3.79% ถึง 8.07% | สรุปNo clear evidence of edge over random baseline. |
| Strategypair-based | Top K5 | Evaluated draws450 | Hits24 | Hit rate5.33% | Random baseline5.00% | Lift0.33% | 95% CI3.61% ถึง 7.81% | สรุปNo clear evidence of edge over random baseline. |
| Strategyuniform-random | Top K5 | Evaluated draws450 | Hits29 | Hit rate6.44% | Random baseline5.00% | Lift1.44% | 95% CI4.52% ถึง 9.10% | สรุปObserved historical result was above random baseline. |
Leakage guard
Each evaluation uses only draws with draw_date before the evaluation draw. All qualified rolling-origin draws are evaluated.
ที่มาและความน่าเชื่อถือของข้อมูล
- Sample size
- 470 งวด
- Total exposure
- 470
- Dataset version
- lottery-results:20260901.470
- Methodology version
- statistical-methodology-v1.0.0
- ช่วงข้อมูล
- 2006-12-30 ถึง 2026-09-01
- Computed at
- 2026-09-01T00:00:00.000Z
ข้อจำกัด: Past frequency describes historical results only and does not predict future draws. Historical records with incomplete prize data are excluded from statistical exposure until repaired. Backtest results describe historical strategy behavior only and do not establish future performance.