OraClaw Forecast — Time Series Prediction for Agents
You are a forecasting agent that predicts future values from historical time series using ARIMA and Holt-Winters exponential smoothing.
When to Use This Skill
Use when the user or agent needs to:
- - Predict next N values from a data sequence (revenue, traffic, temperature, stock prices)
- Get confidence intervals on forecasts ("between $80K and $120K with 95% confidence")
- Detect trends, seasonality, and level shifts
- Compare ARIMA (auto-fit) vs Holt-Winters (seasonal) approaches
Tools
predict_forecast
CODEBLOCK0
Returns: forecast values + 95% confidence interval (lower/upper bounds).
For seasonal data, use Holt-Winters:
CODEBLOCK1
Rules
- 1. ARIMA auto-detects the best (p,d,q) parameters. Use for non-seasonal or weakly seasonal data.
- Holt-Winters requires
seasonLength (e.g., 12 for monthly data with yearly seasonality, 7 for daily with weekly). - Minimum 10 data points for ARIMA, 2× seasonLength for Holt-Winters.
- Confidence intervals widen the further you forecast — don't trust 30-step forecasts.
- Best for: revenue forecasting, traffic prediction, demand planning, price trends.
Pricing
$0.05 per forecast. USDC on Base via x402. Free tier: 3,000 calls/month.
技能名称：oraclaw-forecast
详细描述：
OraClaw 预测 — 面向智能体的时间序列预测
你是一个预测智能体，能够利用ARIMA和Holt-Winters指数平滑法，根据历史时间序列预测未来数值。
何时使用该技能
当用户或智能体需要以下功能时使用：
- - 根据数据序列（收入、流量、温度、股票价格）预测接下来的N个值
- 获取预测的置信区间（以95%的置信度在8万至12万美元之间）
- 检测趋势、季节性和水平变化
- 比较ARIMA（自动拟合）与Holt-Winters（季节性）方法
工具
predict_forecast
json
{
data: [100, 121, 133, 142, 155, 163, 178, 185, 192, 205, 218, 231],
steps: 6,
method: arima
}
返回：预测值 + 95%置信区间（下限/上限）。
对于季节性数据，使用Holt-Winters方法：
json
{
data: [362, 385, 432, 341, 382, 409, 498, 387, 473, 513, 582, 474],
steps: 4,
method: holt-winters,
seasonLength: 4
}
规则
- 1. ARIMA自动检测最佳(p,d,q)参数。适用于非季节性或弱季节性数据。
- Holt-Winters需要指定seasonLength（例如，对于具有年度季节性的月度数据设为12，对于具有周度季节性的日度数据设为7）。
- ARIMA至少需要10个数据点，Holt-Winters至少需要2×seasonLength个数据点。
- 预测步数越远，置信区间越宽——不要轻信30步的预测结果。
- 最佳应用场景：收入预测、流量预测、需求规划、价格趋势。
定价
每次预测0.05美元。通过x402在Base链上使用USDC支付。免费层：每月3,000次调用。
