dennisthiessen/signal-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: stop the position count cap from binding (10 -> 15)

Browse Source 
The capacity bracket study (reports/portfolio-construction-prod505-capacity-
bracket-daily-v1) showed a book whose count cap never binds earns +1.1pp CAGR
over the old 10 -- 51 of 175 paired cohorts better, 2 worse -- at unchanged
drawdown (+0.007pp) and better Calmar in 51 of the 52 cohorts that moved.

The headline EV-per-trade delta is ~0 (+0.001), which is the trap: capacity
does not change trade quality, it changes trade COUNT. Flat EV/trade means the
blocked entries were just as good as the taken ones, so refusing them cost their
whole contribution to return. Judge capacity on CAGR, never on EV per trade.

15 is headroom, not a target. cap15 peaked at 12 positions with zero full-book
skips, so cash plus SIM_NOTIONAL_CAP is the real ceiling and 15/20/None are the
same experiment.

SIM_MAX_POSITIONS and the shadow book's DEFAULT_CAPACITY move together to keep
backtest and production in parity. Historical research arms pass max_positions
explicitly, so their labels and past results are unaffected.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
dennisthiessen
2026-08-05 23:04:21 +02:00
co-authored by Claude Opus 5
parent 07d864cf64
commit 3ff0fd9f1c
2 changed files with 14 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/services/backtest_service.py
+8 -1
View File
@@ -1701,7 +1701,14 @@ def _gate_ablation(candidates: list[dict], activation: dict, threshold: float) -
# the QUALIFIED setups at their detection close, best momentum first while
# slots and cash allow.
SIM_STARTING_CAPITAL = 10_000.0
SIM_MAX_POSITIONS = 10
# Headroom, not a target: the count cap should never bind. The capacity study
# (reports/portfolio-construction-prod505-capacity-bracket-daily-v1) showed a book
# that never hits the count cap earns +1.1pp CAGR over the old 10 (51 cohorts of 175
# better, 2 worse) at unchanged drawdown, because the blocked entries were as good as
# the taken ones — capacity costs trade COUNT, not trade quality. The real ceiling is
# cash plus SIM_NOTIONAL_CAP, which saturates the book near 12 positions, so 15/20/None
# are the same experiment. Judge any future change here on CAGR, never on EV per trade.
SIM_MAX_POSITIONS = 15
SIM_RISK_PER_TRADE = 0.01 # fraction of equity risked per position (entry→stop)
SIM_NOTIONAL_CAP = 0.20 # max fraction of equity per position (no margin)
_EULER_MASCHERONI = 0.5772156649015329
app/services/shadow_book_service.py
+6 -4
View File
@@ -40,10 +40,12 @@ KEY_CAPACITY = "shadow_book_capacity"
KEY_RISK_PCT = "shadow_book_risk_pct"
KEY_START_EQUITY = "shadow_book_start_equity"
# Matches the validated configuration: 10-position book, 1% fixed-fractional
# risk. Start equity is only a sizing base — comparisons are drawn in percent
# and R-multiples, never in raw currency.
DEFAULT_CAPACITY = 10
# Matches the validated configuration: 1% fixed-fractional risk, and a count cap
# set as headroom rather than a target — see backtest_service.SIM_MAX_POSITIONS,
# which this must track. NOTIONAL_CAP below saturates the book near 12 positions,
# so the count cap should simply never bind. Start equity is only a sizing base —
# comparisons are drawn in percent and R-multiples, never in raw currency.
DEFAULT_CAPACITY = 15
DEFAULT_RISK_PCT = 1.0
DEFAULT_START_EQUITY = 100_000.0