The user's design (2026-10-20): at the moment of a buy signal, first recognize WHICH SITUATION the stock is in, then apply the rule written for that situation -- not one set of filters for every stock. Every situation below was met in a real trade or a test. "Detect" = measurable at the buy moment (finished bars only). Rule status: HAVE a rule / PARTIAL / NONE. Proposed rules are tested on 2 years before they go live (OFF by default). Updated 2026-10-20.
[2026-10-22] V2 situations: a situation whose rule is already a v2 check is marked V2. The bots log [S7 V2] SYMBOL: v2 held the buy -- ... whenever v2 held a buy ONLY because of such situations (S6, S7, S8, S14, S15, S21; S12 not logged). Code: entry_situations.V2_COVERED / v2_cover().
| # | Situation | Example | Detect | Rule today | Proposed situation rule |
|---|---|---|---|---|---|
| S1 | Window flip: buy share / straightness jump because a big bar left the 15-min window, not because of new buying | HPK 10/20: 31%→61% buy share, 0.21→0.66 straightness in 1 min, on 1,680 shares; -$47 | buy share up ≥ 20 pts or straightness up ≥ 0.3 in the last 2 min, and the bar that left the window had ≥ 3× the window's average volume | RECORD ONLY (10/21): S1 flush-leave flip -- hold until buyers incl. the flush ≥ 55% (2y: 20 held, 70% losers; isolated) | T7b: then also require price sloping up (5-bar trend rising, +0.3%) AND volume increasing (last 5 min > 5 before, ≥ normal) |
| S2 | Fast price rise / spike in 1-2 minutes | NVAX 10/9, PMI 10/13 (+8% in 30 min) | one of the last 2 bars moved > 2× the normal 1-min range, or 5-bar acceleration ≥ 1.5 ATR | RECORD ONLY (10/21): S2 weak spike -- hold until bars hold the spike middle with buyers ≥ 55% (2y: 88 held -0.238%) | T5: don't block -- wait 1-2 min; buy only if the price holds (no close under the spike bar's midpoint) and v2 still passes |
| S3 | Single block print: one huge trade makes a thin stock look active | RILY 10/12: a 53,660-share bar flipped volume 1.37→1.92× | one bar holds > 50% of the last 15 min's volume | RECORD ONLY (10/22): S3 block print -- hold while the block is in the 15-min window (2y: 49 held -0.275%, both years) | thin_trading: median shares/min over 15 min ≥ floor; ignore the block bar when computing RVOL / buy share |
| S4 | Market-wide bounce: many stocks signal in the same minutes | 10/14: 6 buys 10:40-10:46 on a small IWM bounce, all lost | ≥ 3 watched stocks signal within 5 min | RECORD ONLY (10/22): [S4 CLUSTER] log, ≥ 2 other signals in 5 min + IWM direction | tested (B): only 10 cases in 2 years -- low priority; record only |
| S5 | Star / references disagree right after the buy | TDOC 10/20 (sold after 14 s), PGEN (67 s) | Star's sell fires within 2 min of the buy | HAVE (10/20): noise2 holds while ≥ VWAP and the dip is small | -- (watch live) |
| # | Situation | Example | Detect | Rule today | Proposed situation rule |
|---|---|---|---|---|---|
| S6 | Extended above the open | APPS 9/25 (+5.6%), DXC 10/5, TAL 10/12 (0.7 of its daily range) | % over the open, and the same in daily ATRs | V2 [S6 V2]: max 3% over the open unless a confirmed breakout; + own S6 rule (no breakout exception, record only 10/22) | scale it to the stock: max 0.5-1× daily ATR over the open (v2 option ext_hard_max_atr, OFF; passed the 2-year test 10/7) |
| S7 | Stretched above VWAP | PMI 10/13 (+7..18%), CERT 10/9 | % over VWAP | V2 [S7 V2]: 0 to +2% over VWAP (loosening tested worse) | scale to ATR for calm stocks (TAL: +2% = 0.7 ATR) |
| S8 | Close under resistance | 10/14 losers: room 2.6-7% | % to the 14-day resistance | V2 [S8 V2]: room ≥ 1%; + own S8 rule (5% / ATR, testing 10/22) | C5 room ≥ 5% -- best of A-E (-0.103% vs -0.133%, both halves better) |
| S9 | Gap-down filling to the previous close | TAL 10/12 stalled at 12.86 = previous close | gap down, price within 0.5% under the previous close | RECORD ONLY (10/22): S9 -- hold while the previous close is 0.5-3% above (2y check: 84 buys ~-0.36%) | treat the previous close as resistance (room rule) |
| S10 | Late in the move: the rise confirmed after most of it is done | SNAP 10/12, ANGO / WULF 10/8 (55-75% of the rise done) | move from the V low / day low vs the normal daily range | NONE (v2 confirms late by design) | max_move_x (v2 option, OFF): no buy after ≥ 1.5× the normal move so far |
| # | Situation | Example | Detect | Rule today | Proposed situation rule |
|---|---|---|---|---|---|
| S11 | Bounce after a sell flush (dead-cat) | HPK 10/20 (9:51 flush, 44k shares) | a down bar with ≥ 5× normal volume in the last 30 min | NONE | T3: cool-down 15-30 min AND a higher low must form before a buy |
| S12 | Opening spike, then collapse (first 15 min) | SAIQ / ITG / MAX 10/9 (SAIQ -23%) | minute < 15 | V2 [S12]: 15-bar wait | -- |
| S13 | Deep V turn | BRUN, ANGO, AVO 10/8-10/9 | V low (3 bars each side), drop ≥ 3% | PARTIAL: v2 waits for a steady 15-min rise (buys late) | tested as an entry: no edge (look-ahead removed); as a FILTER: V near VWAP + early + 1st V = recovers 47-50% |
| S14 | Below-VWAP recovery / VWAP reclaim | AGEN 9/28, TRLV | price crossing back over VWAP | V2 [S14 V2]: v2 needs ≥ 0% over VWAP | VWAP-reclaim entry tested 9/29: negative -- keep blocking |
| S15 | Falling on net selling | flow study 9/28 | down ≥ 1% with buy share < 50% | V2 [S15 V2]: v2 "falling on net selling" + buy share ≥ 55% | -- |
| S16 | Lower low by 10:30 | big-winner study 9/27 | 10:00-10:30 low < 9:30-10:00 low | avoid rule exists, OFF | -0.109% alone; +0.087% on ATR ≥ 8% stocks -> test with min_atr_pct |
| S17 | Choppy stock (many Vs today) | -- | ≥ 3 Vs today | avoid rule exists, OFF | -0.120% (cuts 3/4 of trades) -- low priority |
| S18 | Flat bars pinned at the low | BETR 10/8 | ≥ 2 flat bars WITH trades near the low | avoid rule exists, OFF | 40% keep falling vs 27% -- small effect |
| S19 | Absorption (sells hit, price holds) | EV3 path B | sell > buy 3 bars, price not lower | NONE | EV3 tested: no edge with minute data; retest with the ORDER BOOK (bid refilling) |
| # | Situation | Example | Detect | Rule today | Proposed situation rule |
|---|---|---|---|---|---|
| S20 | Calm stock | SNAP / RILY / TAL 10/12 | daily ATR < 8% | HAVE: min_atr_pct (trade bot ON, Star OFF) | threshold test 4-8% (fix #2) |
| S21 | Thin / wide-spread stock | RILY 0.4%, HPK 0.9%, PMI 2-4.5% | spread %, shares/min | V2 [S21 V2]: spread ≤ 1%, ≥ 2,000 shares/min | tighter spread (fix #4), median volume (S3) |
| S22 | Low-float squeeze / halt runner | PMI 10/13 (+56%), WFF 10/12 (halts) | very thin, > 3% spread, > 20% move | PARTIAL: blocked by spread / liquidity / extension | separate "squeeze" setup with its own size / stop rules (idea, untested) |
| S23 | Steady climber on normal volume | TGB / IMMX 9/28, ABSI 10/9 | steady rise, volume 0.5-1.1× normal | blocked by the 1.5× volume rule | loosening tested worse overall -- maybe allow only for ATR ≥ 8% (test) |
| S24 | Market falling / rising (IWM) | 10/14 vs 10/15 | IWM vs open / VWAP at the buy | NONE | tested: IWM at the buy does NOT predict the trade -- no rule |
| S25 | Sector move (crypto miners with bitcoin) | 10/15 BTC +2.7% | BTC since 9:30 for crypto names | NONE | tested (E): no help -- no rule |
| S26 | News / SEC filing today | BETR delisting notice, offerings | news / SEC tags | recording; sec_avoid OFF | news = mover signal (scanner), not a buy signal; SEC tags need the backtest (fix #10) |
| S27 | Re-entry after a loss | -- | a loss in the same stock today | HAVE: only above the last buy | -- |
| S28 | Stock in a "loser" group (group watcher) | 7 buys -$113.62 vs neutral +$20.38 | group label before the buy | NONE (recording) | candidate avoid filter after 2-3 more weeks |
1. Situation tagger (log only first): on every v2 buy signal, tag which situations S1-S28 the stock is in (several can apply at once).
2. Situation rules, each with its own switch and numbers (like the avoid rules): "if S1 then require T7b", "if S2 then wait and confirm",
"if S11 then cool-down + higher low", "if S20 then skip"...
3. Test each situation on 2 years: how often it happens, how its buys do, and whether its rule improves THOSE buys (not the average of all buys).
4. Switch rules on one by one, as with the avoid rules.
| Situation | Buys | Per trade (0.2% cost) | vs the other buys | Verdict |
|---|---|---|---|---|
| S20 calm (ATR < 8%) | 1,525 | -0.175% | not calm: -0.003% (halves -0.16 / +0.14) | BIGGEST harm -- study first |
| S8 room to resistance < 5% | 558 | -0.199% | -0.108%, worse in both halves | harmful |
| S6 extended > 3% over the open | 66 | -0.450% | -0.122%, both halves | harmful (rare: breakout exception) |
| S10 late (move > 1.5x normal) | 249 | -0.185% | -0.126% | mildly harmful |
| S16 lower low by 10:30 | 554 | -0.195% | -0.109% (halves disagree) | unclear |
| S3 block print / S21 thin or wide | 50 / 43 | -0.307% / -0.369% | both halves worse | harmful but rare |
| S1 window flip | 101 | -0.078% | better than average | not harmful -- rule R1 no effect |
| S2 spike | 429 | -0.101% | better than average | not harmful -- waiting (R2) made it WORSE |
| S11 flush bounce | 1,095 | -0.119% | -0.150% | not harmful -- cool-down (R11) made it WORSE |
| S17 choppy | 1,530 | -0.137% | -0.120% | no difference |