Add turnover recording, turnover-control analysis, and real-market check#143
Merged
Conversation
Reviewer-driven additions for the execution-sensitivity paper: - Execution sweep now records per-run turnover (turnover_events). - analyze_turnover_control.py: bins agents into turnover terciles and recomputes E0-vs-E1 Kendall tau within each bin. Within-tercile tau averages 0.63---higher than the full-leaderboard tau (0.24 in high volatility) but well below 1---so turnover is the primary driver of the directional effect yet does not fully explain the reordering. - run_execution_sensitivity_real.py: runs the deterministic agents on real Yahoo OHLCV across the same execution ladder to test whether the leaderboard reordering persists on empirical price/volume paths (no API access; deterministic and reproducible).
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reviewer-driven additions for the execution-sensitivity paper (01): per-run turnover recording, a turnover-controlled ranking-stability analysis (within-tercile tau 0.63 vs full-leaderboard 0.24 - turnover is the primary driver but does not fully explain the reordering), and a real-market hybrid check running deterministic agents on real Yahoo OHLCV across the execution ladder.
Test plan