arima-forecast

SKILLWorkflowcommunity
v0.0.0SpideyHp27MITUpdated 2mo agoSource →

Box-Jenkins ARIMA forecasting judged honestly against the random walk — order picked by ADF+AIC on train only, walk-forward 1-step forecasts with zero look-ahead, RMSE skill vs naive, directional accuracy vs 50%, Ljung-Box residual check, and a sign-trading proof harness with costs. Use for "forecas

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
1Repo stars
1Clients
1Formats
2mo agoLast update
Skill
AuthorSpideyHp27
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Box-Jenkins ARIMA forecasting judged honestly against the random walk — order picked by ADF+AIC on train only, walk-forward 1-step forecasts with zero look-ahead, RMSE skill vs naive, directional accuracy vs 50%, Ljung-Box residual check, and a sign-trading proof harness with costs. Use for "forecast this series", "ARIMA", "does anything predict tomorrow's return". Expects and reports the honest n

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.

Topics

Related in weather