Repository navigation
Conversation
merge updates from vector
Add XGBoost predictor for manufacturing stress forecasts
feat(manufacturing): add notebook workbench and cached LLMP backtest
Expand manufacturing stress data features
…tput Fix/manufacturing agent json output
FRED now truncates BAMLH0A0HYM2 (ICE BofA HY OAS) to a rolling 3-year window, which silently zeroed out every fit-at-origin training example for the logistic/XGBoost/agent predictors across both backtest windows (build_feature_snapshot requires all features present or drops the row). Replace it with BAA10Y (Moody's Baa corporate yield minus 10Y Treasury), which has full history back to 1986, and rename HY_SPREAD to CREDIT_SPREAD throughout to reflect the new source. Also removes the GSCPI data source and its test, and finishes the STATISTICAL_FEATURE_SERIES_IDS -> FEATURE_SERIES_IDS cleanup in the logistic/XGBoost predictors.
Lets the tune/confirm sweep test alternative stress-label definitions (e.g. -1.5% trailing 3-month IPMAN decline instead of the -2.0% default) without editing code. Threshold changes redefine the target, so results across different thresholds are not directly comparable.
Fix manufacturing-stress credit spread feature (FRED truncation)
Improve adaptive-agent structured response handling and document the paired Lite/Advanced evaluation outputs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Include remaining notebook updates and generated adaptive-agent and all-model report packages. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
…on history Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Backtesting lives in the adaptive model comparison notebook. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot/push to bmo c2
… evaluation - Walk-forward adaptive agent (run_adaptive_walk_forward.py) with an OutcomeLedger: the agent sees only forecast outcomes published by each origin, and strategy tools refuse hypothesis outcomes that do not cite a resolved origin. Fixes single-forecast self-confirmation of hypotheses. - Full-history deterministic evaluation (2003-2024, 264 origins, 20 stress months) with block-bootstrap intervals, horizon-aware Diebold-Mariano tests, and Murphy decomposition (evaluation_stats.py, run_full_history.py). - Fix logistic/XGBoost fallback forecasting exactly zero when feature-limited training rows contain no events; fall back to the visible label base rate. - Vectorised fit-at-origin training rows (~100x faster, exact match). - Untrack __pycache__, remove stray nested report path, drop dead code, fix adaptive report output path. - Docs: manufacturing README, root README, implementations README, roadmap, AGENTS.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A lite-model walk-forward that asked each forecast call to also maintain the strategy made zero strategy mutations over 76 origins. Learning now happens in a dedicated review call, run every --review-every origins and after any newly published stress outcome. Reviews see resolved forecasts with the signals at each origin, so hypotheses can name signal conditions. Forecast calls read the strategy but cannot change it; --review-every 0 restores the single-call design for comparison. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Manufacturing enhancements
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Clickup Ticket(s): Link(s) if applicable.
Type of Change
Changes Made
Testing
uv run pytest tests/)uv run mypy <src_dir>)uv run ruff check src_dir/)Manual testing details:
Screenshots/Recordings
Related Issues
Deployment Notes
Checklist