This platform does not optimize for finding trades. It optimizes for discovering, measuring, validating, and continuously improving statistically defensible trading edges.
What this page is
This Experiment Dashboard is a live view into five parts working together: a Research Registry of every hypothesis registered before it's evaluated (never after — no fitting a question to a result already known), an Evidence Ledger of every resolved signal, and a Confidence Engine that labels every conclusion by its real evidence strength rather than a bare number. The reasoning behind each — this project's Research Notebook — is maintained internally alongside the code that produces it. Observational only — nothing on this page gates a trade or changes scoring_engine.py's weights.
Confidence Engine labels, by real sample size
INSUFFICIENT
n<20 — too small to conclude anything
WEAK
n≥20 but effect size/significance still thin
MODERATE
n≥50 with a real effect
STRONG
n≥100 with a real effect
LOW VARIANCE
a separate check (not sample-size-based) — the factor barely varies across signals, so a low-vs-high comparison isn't meaningful regardless of n.
Hypotheses registered
3Registered before the result is known
Resolved stock signals
1,819With a real scoring breakdown on file
Auto-trade decisions
37,2332,024 accepted · 35,209 rejected
Executed trades on file
3,4663,466 with a regime snapshot
Data Quality
stock missing exit price
58/3941 resolved stock signals are quarantined (incomplete_exit, legacy, excluded from all stats)
WARN
crypto missing exit price
0/5777 resolved crypto signals have an outcome but no exit_price/pct_gain
OK
outcome pct gain mismatch
1/3883 resolved stock signals have outcome/pct_gain sign mismatches (e.g. outcome=LOSS with a positive pct_gain)
FAIL
stopped out without verdict
0/986 stopped-out signals have no verdict field - expected for anything logged before fix #193, not a bug
OK
shadow score neutral dilution
436/1880 shadow-scored signals have >50% of factors on neutral-credit fallback
WARN
profile cache staleness
Last full refresh 88 days ago (21769 symbols; expected roughly monthly)
FAIL
coingecko cache health
1813 cached entries, oldest 1984.8h old
OK
regime snapshot staleness
Most recent regime snapshot 26.7h old (expected within 48h)
OK
order flow archive readable
1 of 93 sealed order-flow archives cannot be decompressed to the end: the rows past each cut are lost and excluded from every order-flow statistic (the rows before it are read): order_flow_journal-2026-09-16.jsonl.gz (245339 bytes) - median archive is 5,228,226 bytes
FAIL
venue rechecks overdue
every venue's re-check date is in the future
OK
Regime-Conditioned Performance
Regime the broad market's state when a trade was opened, such as trending or range-bound, from the stored market-regime snapshot.
RANGE BOUND HIGH VOL
65 trades
· win rate 60.0%
· Sharpe 0.03
RANGE BOUND LOW VOL
801 trades
· win rate 63.2%
· Sharpe 0.28
TRENDING HIGH VOL
88 trades
· win rate 48.9%
· Sharpe -0.00
TRENDING LOW VOL
2,512 trades
· win rate 64.3%
· Sharpe 0.26
Auto-Trade Rejection Report
Exactly why signals reaching AutoTrader.on_signal() are accepted or rejected, by the specific gate that decided it — real, persisted data (fix #349), not reconstructed from logs that don't survive this project's own log retention.
Covering 2026-08-23 to 2026-11-21.
6,154 (17.5% of rejections)
· 1929/6154 within 10% of clearing
duplicate position
4,940 (14.0% of rejections)
max positions
4,648 (13.2% of rejections)
smc bearish bias
3,617 (10.3% of rejections)
min rr
3,426 (9.7% of rejections)
· 135/3426 within 10% of clearing
not halal compliant
1,859 (5.3% of rejections)
min confluence
1,015 (2.9% of rejections)
· 853/1015 within 10% of clearing
portfolio exposure
668 (1.9% of rejections)
min rel vol
491 (1.4% of rejections)
· 33/491 within 10% of clearing
crypto results pause
464 (1.3% of rejections)
stock signal barred
340 (1.0% of rejections)
compliance unresolved
181 (0.5% of rejections)
news blackout
172 (0.5% of rejections)
unpriceable symbol
162 (0.5% of rejections)
stale price invalidates bracket
102 (0.3% of rejections)
market closed
82 (0.2% of rejections)
crypto stop too wide
45 (0.1% of rejections)
min swing confluence
37 (0.1% of rejections)
· 33/37 within 10% of clearing
min rr at execution
17 (0.0% of rejections)
crypto signal barred
6 (0.0% of rejections)
sizing constraint
2 (0.0% of rejections)
broker rejected
1 (0.0% of rejections)
daily loss limit
1 (0.0% of rejections)
Scalp Stop-Width Filtering
2026-07-23: real closed stock trades had stops as tight as 0.15%-2.2% of entry — tighter than ordinary intraday noise, contributing to a 16.7% stock win rate vs crypto's 57.9% over the same window. MIN_SCALP_STOP_PCT now rejects a stop that's too tight, the same way MAX_SCALP_STOP_PCT already rejected one too wide — a distinct, earlier stage than the rejection report above (a signal filtered here never reaches on_signal() at all).
Covering 2026-09-01 to 2026-11-20.
too tight (avg 0.52%)
7,490
too wide (avg 6.5%)
1,706
BREAKOUT
315 too tight · 0 too wide
BULL_FLAG
2 too tight · 71 too wide
CANDLE
2685 too tight · 37 too wide
EMA_PULL
1023 too tight · 4 too wide
FIB_BOUNCE
272 too tight · 0 too wide
GAP_GO
21 too tight · 821 too wide
HOD_BREAK
409 too tight · 39 too wide
MOMENTUM
1145 too tight · 19 too wide · 527 other
ORB
76 too tight · 275 too wide
PM_HIGH
33 too tight · 141 too wide
SETUP
563 too tight · 0 too wide
VWAP
946 too tight · 299 too wide
GAP_GO Entry Slippage
Real case, 2026-07-23: a GAP_GO market order intended to enter CITR at $5.04 filled at $5.96 (18.25% slippage), while position sizing had already used the tiny intended risk-per-share — the stop stayed fixed near the pre-gap level, turning a controlled 1%-risk trade into a $1,267 loss. GAP_GO entries are now a marketable limit order bounded at entry × (1 + MAX_GAP_GO_ENTRY_SLIPPAGE) instead of an unrestricted market order.
GAP_GO trades
7
with bounded entry
2
avg slippage
3.628%
max slippage
18.254%
Halal ETF Constituents Not Yet Tracked
Real holdings of SPUS/HLAL/MNZL (from their own SEC Form N-PORT filings) that don't match any symbol already on the watchlist by company name. A review list only — N-PORT filings never include a ticker, so matching is by name and inherently fuzzy. Nothing here is added automatically; each candidate needs its own live ticker/listing check first, same discipline that caught “AMAL” resolving to an unrelated bank.
403 watchlist symbols confirmed held by a real fund ·
84 real holdings not matched to the watchlist
as of 2026-10-24
AGCO Corp (001084102)
MNZL · 0.02%
Acuity Inc (00508Y102)
MNZL · 0.02%
Antero Resources Corp (03674X106)
MNZL · 0.04%
Apellis Pharmaceuticals Inc (03753U106)
MNZL · 0.01%
Ashland Inc (044186104)
MNZL · 0.01%
AvalonBay Communities Inc (053484101)
MNZL · 0.10%
Avnet Inc (053807103)
MNZL · 0.03%
BellRing Brands Inc (07831C103)
MNZL · 0.01%
BorgWarner Inc (099724106)
MNZL · 0.04%
Bright Horizons Family Solutions Inc (109194100)
MNZL · 0.01%
Brookfield Renewable Corp (11285B108)
MNZL · 0.02%
Builders FirstSource Inc (12008R107)
MNZL · 0.03%
CDW Corp/DE (12514G108)
MNZL · 0.09%
CH Robinson Worldwide Inc (12541W209)
MNZL · 0.07%
CLEAN HARBORS INC COM (184496107)
MNZL · 0.06%
Cava Group Inc (148929102)
MNZL · 0.03%
Choice Hotels International Inc (169905106)
MNZL · 0.00%
ConocoPhillips (20825C104)
HLAL, MNZL · 0.51%
DR Horton Inc (23331A109)
HLAL, MNZL · 0.15%
Dick's Sporting Goods Inc (253393102)
MNZL · 0.05%
Dillard's Inc (254067101)
MNZL · 0.00%
Eagle Materials Inc (26969P108)
MNZL · 0.02%
Elastic NV (N/A)
MNZL · 0.02%
Electronic Arts Inc (285512109)
HLAL · 0.18%
Eli Lilly & Co (532457108)
HLAL, MNZL · 2.68%
Envista Holdings Corp (29415F104)
MNZL · 0.01%
Equity Residential (29476L107)
MNZL · 0.09%
Esab Corp (29605J106)
MNZL · 0.02%
Everpure Inc (74624M102)
MNZL · 0.08%
Expeditors International of Wa (302130109)
HLAL · 0.07%
Ferguson Enterprises Inc (31488V107)
HLAL, MNZL · 0.18%
Fortune Brands Innovations Inc (34964C106)
MNZL · 0.01%
GXO Logistics Inc (36262G101)
MNZL · 0.02%
Gap Inc/The (364760108)
MNZL · 0.02%
Gates Industrial Corp PLC (N/A)
MNZL · 0.02%
Globant SA (N/A)
MNZL · 0.01%
Hologic Inc (436440101)
HLAL · 0.06%
Huntsman Corp (447011107)
MNZL · 0.01%
IAC Inc (44891N208)
MNZL · 0.01%
IFF (459506101)
HLAL · 0.08%
Insmed Inc (457669307)
MNZL · 0.10%
JB Hunt Transport Services Inc (445658107)
HLAL, MNZL · 0.06%
Kenvue Inc (49177J102)
HLAL, MNZL · 0.13%
Kyndryl Holdings Inc (50155Q100)
MNZL · 0.01%
Lear Corp (521865204)
MNZL · 0.02%
Liberty Broadband Corp (530307305)
MNZL · 0.01%
Liberty Live Holdings Inc (530909308)
MNZL · 0.02%
Liberty Media Corp-Liberty For (531229771)
HLAL · 0.01%
Lineage Inc (53566V106)
MNZL · 0.01%
Lowe's Cos Inc (548661107)
MNZL · 0.52%
+ 34 more, not shown
Signal-Level Factor Research
Based on 1819 resolved stock signals with a real scoring breakdown on file — low vs high tercile win rate per factor.
liquidity structure
stuck at 0.0 for most signals — not enough spread to compare yet
LOW VARIANCE
vwap
stuck at 7.2 for most signals — not enough spread to compare yet
LOW VARIANCE
momentum
low `33.8%` (n=606) vs high `36.9%` (n=607)
MODERATE
volume
low `31.2%` (n=606) vs high `40.0%` (n=607)
MODERATE
smc
stuck at 0.0 for most signals — not enough spread to compare yet
LOW VARIANCE
trend
low `8.5%` (n=82) vs high `12.0%` (n=83)
WEAK
sentiment
low `25.9%` (n=606) vs high `41.2%` (n=607)
MODERATE
fundamentals
low `38.6%` (n=606) vs high `35.4%` (n=607)
MODERATE
risk liquidity
low `37.0%` (n=606) vs high `26.9%` (n=607)
MODERATE
Feature Redundancy
liquidity_structure and smc — insufficient variance to assess
r=0.922 (artifact)
Research Registry
Every hypothesis this platform tests, registered here before its result is known — a question can't be quietly reworded after the fact to match whatever the data happened to show.
STRONGn=838 vs 1829
Does RSI >= 60 at signal time outperform RSI < 60?
mean -1.13% (n=838) vs -0.64% (n=1829) · p=0.003
WEAKn=491 vs 1490
Does an SMC grade above 50 (real structural credit, per scoring_engine.py's own fallback rule) outperform 50 or below?
mean -0.82% (n=491) vs -0.60% (n=1490) · p=0.182
WEAKn=76 vs 1531
Does a signal in this week's rotating-in sector outperform one that isn't?
mean -0.44% (n=76) vs -0.21% (n=1531) · p=0.163
Evidence Ledger
The most recent resolved signals feeding every conclusion above — every one WIN/LOSS, nothing excluded or reworded after the fact.