Entry knowledge base

Every entry idea tested from 2026-09-17 to 2026-10-11, what it showed, and the resulting list of what NOT to trade. Real cost = about 0.2% per round trip (measured from broker fills 10/7). "Year 1 / year 2" = tested on two separate halves of the data. Updated 2026-10-12. Scripts and full logs are named in each row.

1. Do NOT trade -- avoid list (backed by data)

#Do not buy when...EvidenceStrength
A1Price is more than ~2% above VWAP (stretched)Stop hit first 40-48% vs 25% below VWAP, in 3 separate studies (9/26-9/27). Loosening the live 0..+2% band to +3% or 0.3x ATR: the extra trades lose -0.26% / -0.29% each over 2 years (10/9).strong
A2The stock is calm: daily ATR under ~8%Live v2 buys over 2 years: ATR < 8% = -0.16%/trade (1,482 trades, -$3,914) in every quarter; ATR >= 8% = about break-even (+0.02%) (10/10). Not enforced yet -- your decision.strong
A3The volume rule fails (volume so far < 1.5x normal)Looser volume 1.2x / 1.0x / off: extra trades lose -0.21% to -0.23% each, both halves (10/9). The 10/9 near misses (ABSI, CLF...) were winners in hindsight only.strong
A4The rise is not steady (15-min smoothness < 0.7, straightness < 0.5)Looser 0.6/0.4 or 0.5/0.35: extra trades -0.23% to -0.33% each (10/9).strong
A5Price is already far above the open (more than 3%, unless a confirmed real breakout)Loosening to 0.5x / 0.75x / 1x ATR: extra trades -0.18% / -0.27% / -0.26% (10/9). 20-day study: buys 3-10% above open -$624 (9/26). APPS bought at +5.6% reversed at once (9/25).strong
A6Stock is falling on net selling (down >= 1% with sellers dominating)Keeps falling: -0.58% / -0.70% over the next 60 min, both halves, 660 stock-days (flow study 9/28). Same in the VWAP-reclaim study (9/29).strong
A7Late in the day (after ~14:30)2-year v2 replay: buys after 14:30 median -0.36%/trade; 14:30-15:00 negative both years (10/8). Late +2% touches almost never reach +5% (4%) (10/8). Late Vs (after 13:00) recover only 7-9% of the time (10/11).strong
A8The first 15 minutes (before 9:45)The 15-bar wait blocked SAIQ / ITG / MAX spikes that then collapsed (SAIQ -23%) (10/9). 20-day bar study: 9:30-10:00 entries -$441 (9/26).medium
A9Heavy volume spikes (last-15-min volume > 5x normal, climax bars, acceleration at 10:00)Heavy volume vs normal at 11-12 -> fade (AUC 0.42); high acceleration at 10:00 -> fade (AUC 0.41); climax events -21% to the close (5 cases) (speed study 9/28). Heavy-volume V recovery -8 to -10% (group study 9/29, small n). The X1 climax EXIT is built on this and passed 2 years.medium
A10Gap over ~10%Big-winner study: gaps over 10% faded about -8% from the open on average; gaps 5-10% were the best (9/27, 21 days).medium (small)
A11A lower low by 10:30Only 2% of those became +5% winners vs 58 of 63 winners holding a higher low (big-winner study 9/27).medium (small)
A12Spread over 1% or under 2,000 shares/minKept as live guards (spread since 9/28, liquidity since 10/7). Wide spreads eat the small gains (real cost already 0.2%).rule kept
A13A V that is far below VWAP, late, or the 3rd+ V of the dayOpening-spike Vs: more than 5% under VWAP -> 80% stay weak, 7% recover; V after 13:10 -> 7-9% recover; 20th V -> 9% (2 years, both years equal, 10/11).strong (as a filter)
A14Flat bars with trades right at the low (price pinned, O=H=L=C)40% keep falling vs 27% without flat bars (125k Vs, 10/11). Not a base -- usually sellers working the price.medium
A15Breakout buys (vs pullbacks), and re-buys below a losing trade's entry20-day bar study: breakouts -$532 vs pullbacks about 0 (9/26). Re-entry only above the losing trade's entry was better on all 4 test days (9/23, live since).medium
A16SEC filing: offering / dilution / delisting noticeRecording only since 10/7 (BETR delisting notice 10/9 while on the watch list). Not tested yet -- needs the 10-year tag backtest.untested

2. Entry ideas tested that did NOT work -- do not rebuild without new data

DateIdeaResultWhy it failed
9/22Live entry-quality score (gate at 55)Looked better on 2 days (in-sample), replaced later2 days, weights fitted on the same days
9/23-9/28Setup J: trade plan, R:R >= 2, context rules, 5-day levels, slope ruleMixed: +$145 on 6 days tick, -$98 / +$103 on 20 days bars; replaced by v2 on 9/29Results flipped between test sets; few trades
9/26-9/27Shadow PASS gate (entry_rules: VAS, imbalance, relative strength, volume trend)20-day tick: J +$21 vs gate +$6Features flat over 64k snapshots; only VWAP distance mattered
9/27trade1 entry_rules (620 picks, hold to close)311 up / 309 down, -$1,275No value separates rising from falling picks (AUC <= 0.56)
9/27Buy early leaders at 10:30-$517 to -$1,610 over 21 daysLeaders by 10:30 are not more likely to keep going
9/28Speed / smoothness signals (move >= 2x normal + smooth)Held to close -0.6% to -2% vs time-matched base5-stock pattern did not generalize (654 stock-days)
9/28Buy volume / net buying / "quiet demand"AUC 0.49-0.50 for the next 30/60 minBuy volume adds nothing beyond price
9/29VWAP reclaim after an early spike (AGEN idea)Every variant lost, both halves (-0.5% to -1.9% with stop)Pullbacks below VWAP on selling keep falling
9/29-9/30Playbook groups at 10:15 (ALLOW / AVOID)In-sample good; 6-month out-of-sample ALLOW +0.00% vs AVOID -0.03%Overfit to 23 days
10/1-10/4Analog matching / Star Follow buys / reference trader / playbook advisorAll versions negative (-274% to -456% sums); advisor lowered P/L (+$118 -> +$69); Star buys -$197 / -$275Similar days predict MOVEMENT, not direction
10/3Opening-range breakout (ORB, 12 variants, 503 days)All lose (best -0.09%/trade)Same as breakout finding
10/7-10/8Pick only the best 1-5 trades per day (8 metrics)At real cost: break-even at best (v3 score top 1/day: -0.08% / 0.00%)Edge per trade smaller than cost
10/7-10/10Deep-V entry (10 years)Looked +0.16% to +0.22%; after fixing a 2-bar look-ahead: -0.07% to -0.10%, same as luckThe edge was future data
10/8Buy the moment a stock touches +2% / +3% over the open (7 styles, 5 years)Every style loses at 0.2%; the ">2% over VWAP + ATR >= 9.4% + early" pocket failed at checkpoint pricesTouch is common (38-49% of stock-days); no direction info
10/9Group filters at 9:45-11:30 (16 groups)Only "winner" group +0.22% train -> -0.17% testOverfit
10/9Group + up-trend confirmation (21 groups x 5 rules: new high, VWAP reclaim, V turn, 9:45 break, smooth trend)0 groups with an edge even in training; -0.15% to -0.45%/tradeAfter confirmation only ~1.3% move left
10/9Looser v2 rules (12 variants: volume, steady rise, extension, VWAP band)Every variant worse; extra trades -0.18% to -0.33%The rules block losers (see list 1)
10/10Buying pressure at the V turn (buy share 3/5 min, pressure shift, sell dry-up, net flow)Reversal AUC 0.53-0.56, winning trade AUC 0.50; all filters -0.08% to -0.24%Pressure seen too late; stop under the low too wide
10/11Flat consolidation before the recovery, then buy > sell-0.19% to -0.22%/trade, same as control; flat near the low = MORE fallsFlat bars = no trades / sellers pinning price
10/11Style A (opening spike -> collapse -> V) recovery predictionRecovery predictable (AUC 0.77) but trades lose (-0.09% to -0.14%); best filter overfit (+0.26% -> -0.09%)The Vs that recover are shallow: too little room to pay the cost
10/13EV3 (entry version 3) -- the user's VWAP + buy-flow entry: close >= +1% over VWAP (over +3% needs a confirmed break-up); path A gradual rise with buy volume last 3 min > 3 before; path B absorption (sells > buys 3 bars, price holding) then buyers; exit = 1/4 give-back (15c or 1%), volatility stop 6 variants, 510 days: -0.21% to -0.24%/trade both years (gross ~0.00%), 43-55 signals/day; absorption no better (-0.21%); first signal per stock-day -0.22%; best slice 9:45-10:30 first signals -0.19% (gross +0.01%)Conditions are common and carry no direction: same as random after the cost

3. What DID work / keep

ItemEvidenceStatus
Scanner score v3 (daily ATR %, gap size, premarket volume)Better than the old score in every one of 11 years (10 years, 399k stock-days)trade bot; Star bot back on the old score from 10/12 (A/B)
The v2 entry rules as they are (volume, room, buy share, steady rise, VWAP 0..+2%, max 3% over open, 15-bar wait, spread, liquidity)Every loosening tested worse (10/9)live both bots
Volatile stocks only (ATR >= 8%)About break-even vs -0.16%/trade on calm stocks (2 years)not enabled -- decision pending
Limit orders at the ask (buy) / bid (sell)Mid limits filled 0 of 8; ask limits 3 of 3 in ~5 s (10/8)live both bots from 10/9
Exits: min stop 2%, smooth exit, X1 climax exit2% stop +$369 vs 1% +$282 (24 days); X1 confirmed on 2 yearslive (trade bot)
Star's sellsRecent 7 days: better on 28 of 49 trades; 2-year test: worseStar bot live; watching

4. The pattern behind all of it

The moves are real -- about 12 scanner stocks a day drop 3%+ and rise 3%+ from a V, and 33 of 96 rose 3%+ on 10/9 -- but every signal that can be known at the moment of buying (price shape, minute bars, trade-by-trade buy/sell volume, flat bars, groups, similar past days) separates winners from losers only after the fact. By the time a move is confirmed, too little of it is left to pay the ~0.2% cost and a stop. What reliably helps is avoiding (list 1), picking volatile stocks (v3 score), cheaper execution, and exits.

Still untested (needs new data being recorded now): order-book pressure (bid vs ask size, trade bot from 10/12), SEC filing tags (since 10/7), and more live days of Star's sells.

5. Avoid rules as switches -- 2-year replay (10/12-10/13)

Live v2 buys, every signal, 503 days, 0.2% cost; each rule ON alone (real replay). Base: 2,012 trades, -0.133%/trade. No rule alone makes entries positive. Best: min_atr_pct 411 trades -0.007% (halves -0.20% / +0.18%); lower_low_by_1030 -0.109%; max_above_open / breakout_exception -0.129%; choppy_many_vs -0.120% (482 trades). Worse than base: heavy_volume -0.190%, recent_climax -0.186%, no_buy_after -0.152% (late buys were better than average here), max_gap -0.139%. No effect (v2 already covers): no_buy_before, max_vwap_pct, net_selling_drop. ALL ON: 18 trades -0.473%. On ATR >= 8% stocks: lower_low_by_1030 +0.087% (262), max_above_open +0.011% -> pair test pending.

6. News (Benzinga, 2 years, 10/13)

Top-30 picks with news known at the open reach +5% far more often (39-41% vs 26-29%, both years; "why moving" 56-58%, guidance 50-52%, FDA 51-53%) but do not close better (offerings close about -2%). The bot's buys: any news -0.198% / +0.004% vs no news -0.189% / -0.158% (year 1 / year 2) -- not stable; price-target up/down buys lose both years. News = a MOVER signal (use in the scanner), not a buy signal.