About · 说明
English
What the site publishes
Every hour the site publishes, for BTC/USDT, a 24-hour price range: the predicted high and low at two confidence levels (q50 — "half the time the high stays below this"; q90 — "nine times out of ten the high stays below this"), plus a range for the close 24 hours later. Alongside it comes a volatility level, which is the predicted 24-hour amplitude placed against its own history: low (below the 30th percentile), normal (30–70), elevated (70–90), extreme (90th percentile and above). Direction probabilities (up / down / flat) are shown only as a reference, in a secondary position.
How to read the coverage numbers
Coverage is the share of past predictions where the actual high stayed below the predicted q90 high, and the actual low stayed above the q90 low; the target is 90% for each side, and 80% for the close range. Every coverage figure is printed with its window and sample size (for example "30 days · 720 predictions"). A number without those two labels is not published. Small samples move a lot; read the window before the percentage. We do not publish a direction hit rate.
Data sources
| Data | Source | Used for |
|---|---|---|
| BTC/USDT hourly candles / 小时 K 线 | Binance spot / 币安现货 | price features and targets / 价格特征与预测目标 |
| Taker buy volume / 主动买入量 | Binance spot / 币安现货 | buy-sell pressure / 买卖力量 |
| Funding rate / 资金费率 | Binance USDT-M futures / 币安合约 | long-short crowding / 多空拥挤度 |
| Open interest, long-short ratios / 持仓量、多空比、大户比、主动买卖比 | Binance USDT-M futures / 币安合约 | leverage and positioning / 杠杆与分歧 |
| Premium index / 合约溢价指数 | Binance USDT-M futures / 币安合约 | spot-futures basis / 期现价差 |
| Fear & Greed index / 恐惧贪婪指数 | alternative.me | sentiment / 情绪 |
| DVOL implied volatility / DVOL 隐含波动率 | Deribit | options-market expectation and benchmark / 期权市场预期与标杆 |
All sources are public. Each feature only uses values that were already known at the time of the prediction; when a source is delayed the page marks it grey.
Method
The range model is a LightGBM regressor for the 24-hour amplitude, whose output is turned into high / low / close quantiles by a piecewise calibration fitted on the last part of the training window. Models are evaluated by walk-forward testing: each day is predicted using only data available before it. The direction models (gradient boosting, random forest, logistic regression) are ensembled and must beat a plain baseline to be used at all; on our tests they rarely do, which is why direction is a reference and the range is the product.
Update cadence
Data is pulled every hour; a prediction is made five minutes past each hour; 24 hours later it is reconciled against the actual high, low and close, and the result goes into the history page and the coverage figures. Models are retrained weekly, and earlier if coverage degrades.
Limits
Ranges are statistical estimates and will be exceeded — by design about one time in ten at q90. Sudden news, exchange outages or data-feed delays are not something the model can see in advance. Nothing here is investment advice; see the terms.
中文
本站输出什么
本站每小时发布 BTC/USDT 的未来 24 小时价格区间：两档置信度下的预测最高价与最低价（q50 ——「一半概率最高价不超过它」； q90 ——「九成情况最高价不超过它」），以及 24 小时后收盘价的区间。同时给出波动预警级别，即预测振幅在自身历史中的分位：偏低（低于 30%）、正常（30–70%）、偏高（70–90%）、极高（90% 及以上）。 方向概率（涨 / 跌 / 震荡）只作参考，放在次要位置。
覆盖率怎么读
覆盖率 = 过去的预测中，实际最高价没有超过预测 q90 上沿、实际最低价没有跌破 q90 下沿的比例；两侧目标各为 90%，收盘价区间目标 80%。 每个覆盖率数字都带统计窗口和样本数（例如「30 天 · 720 次」），没有这两个标注的数字本站不发布。 样本少时数字波动很大，先看窗口再看百分比。本站不发布方向命中率。
数据来源
见上表（全部为公开接口）。每个特征只用预测时刻已经可以知道的数据；某个源延迟时页面会标灰。
模型方法
区间模型是对 24 小时振幅做回归的 LightGBM，再用训练窗口末段拟合的分段校准把输出转换成最高 / 最低 / 收盘价的分位数。 评估采用 walk-forward：每一天只用它之前的数据训练与预测。方向模型（梯度提升、随机森林、逻辑回归）做集成， 必须超过朴素基线才会被采用；在我们的测试里它们很少做到，所以方向只是参考，区间才是产品。
更新节奏
每小时拉取数据；每小时第 5 分钟预测一次；24 小时后与实际最高 / 最低 / 收盘对账，结果进入历史页与覆盖率。模型每周重训，覆盖率下滑时提前重训。
局限
区间是统计估计，会被突破——按设计 q90 大约十次里有一次。突发消息、交易所故障、数据源延迟都不是模型能提前看到的。 本站内容不构成投资意见，详见用户协议。