Crypto Research Labs
ZH ▾
GitHub

← 全部假设

H-029: H-027 的实盘复现:12:00 UTC 前发布的每日方向预测

—  类别: 预测 · 状态: 已注册

每日方向预测在实时检验中有效吗? 数据正在积累中。预注册的检验将在积累一年数据后于 2027-11-01 进行。

已收集前向数据:0/368 天(0.0%)。首次检验日期 2027-11-01。

结果

技术细节由引擎生成,以英文显示。

Sharpe:单位风险的收益(越高越好)。CAGR:年均增长率。最大回撤:从峰值的最大跌幅。p 值:结果来自运气的概率(越低越好)。“持有”列为同一资产、同一时间段的买入持有结果。 术语

暂无引擎结果:该研究仅作记录保存,不会重新运行。

为什么可能有效

H-027 can only use history, where the model is fitted with hindsight about which inputs exist and external data may have been revised. This repeats the exact model live from 2026-10-29. Every morning the workflow computes the forecasts from yesterday's close with that month's model (fitted on the month's first day, stored once in datasets/forecast_models/ and never refitted) and appends them to datasets/forecast_log.csv; the commit to GitHub proves they existed before the outcome. Only forecasts published before 12:00 UTC count; the outcome runs from the open of the 12:00 UTC hourly candle to the next day's (datasets/noon_prices.csv: Binance hourly files, Gate.io API), so the real delay between data and trade is in the test. Same pooled Brier-skill test against the base rate and the same paper portfolio (share = probability, 10-point band, fees and slippage), first tested after about a year of live forecasts. Shares alpha with H-030 (0.05 / 2).

结论历史

预注册规范

kind: forecast_live
target: direction
model:
  type: pooled_logit
  features:
  - r1
  - r3
  - r7
  - r30
  - d50
  - d200
  - v7
  - v30
  - btc_r1
  - btc_r7
  - funding
  - fear_greed
  - stable30
  - flow7
  zscore_window: 365
  zscore_min_periods: 180
  clip: 5
  l2: 1.0
  refit: monthly
  external_lag: 1
  ffill_limit: 3
universe:
- BTCUSDT
- ETHUSDT
- SOLUSDT
- BNBUSDT
- XRPUSDT
- ADAUSDT
- LTCUSDT
- LINKUSDT
- DOGEUSDT
- XLMUSDT
- TRXUSDT
- EVERUSDT
- GRAMUSDT
costs:
  default: 0.001
  EVERUSDT: 0.004
  GRAMUSDT: 0.004
portfolio:
  weight: probability
  band: 0.1
execution:
  time_utc: '12:00'
periods:
- name: forward
  start: '2026-10-29'
significance:
  method: circular_shift
  n: 2000
  alpha: 0.025
criterion:
  metric: brier_skill
  pooled: true