Recommendations
0 to acquire · 3 to dispose
| Ticker | Name | Close | Action | Action Price Where to act — a buy-limit on a pullback or a buy-stop above resistance, not the current price. Sanity-check vs Close: on a held name, an action price stranded above the close means the queued level was set when the stock was higher — stale, awaiting reprice. | Stop The risk-defined exit, set below the entry for a long (~1.2–1.8×ATR). A held long whose Stop sits at/above the Close is already below its stop — a stale box awaiting reprice. | 1wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | 4wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | 12wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | Rationale |
|---|---|---|---|---|---|---|---|---|---|
| AIQ | Global X AI & Tech ETF | 63.08 | SELL ALL | 63.08 | 63.90 | 63.00 (-0.1%) | 63.46 (+0.6%) | 67.94 (+7.7%) | Selling the AI/tech basket because the bond market broke the trade: the 10-year jumped 8bp to 4.91%, its highest since 2023, mortgage rates crossed 7% and September rate-HIKE odds ran to ~69% into the 09-16 FOMC -- long-duration AI is the most rate-sensitive corner of the tape and AIQ fell 1.61% against a 0.65% Nasdaq. It closed, below the stop written last session, at the very bottom of its daily range, and the model's own four-week forecast now sits below our cost -- it does not see the position getting back to breakeven. Take the small loss on the stop rather than fund a hope. OPERATIONAL: 09-09 pre-commitment ('a second consecutive NO TRADE, or a close below, is an exit') fires on the close leg -- broken by /1.28%. Conviction trail 90>62>0>56. L2 NOT claimed: 12wk +7.71% is positive; exit rests on written stop + conviction collapse + below-cost Est_4W. G1/G2/G3 N/A (stop-break contrast case). COUNTERWEIGHT: Oracle +7% AH on a Q1 FY27 beat may gap AI up at the 09-11 open -- apply L8 gap-reprice if open gaps >~1.5%, do not cancel. Valuation blind (NA_ETF, val_adj 0). ADR-0019: position unreconciled (JSON). · news |
| QQQ | Invesco QQQ (Nasdaq-100) | 708.69 | SELL ALL | 708.69 | 715.15 | 706.73 (-0.3%) | 713.48 (+0.7%) | 755.72 (+6.6%) | Exiting the Nasdaq-100 on a fourth straight down day driven by rates, not earnings: the 10-year hit 4.91% and the 30-year 5.35%, and this time megacap led the decline -- QQQ fell 1.06% against the Composite's 0.65%. The close of broke the stop we have carried since the position opened and finished below its 10-, 20- and 50-day averages, with conviction decaying 75>69>63>52 over four sessions. The model's four-week view is below our cost, so holding is paying to wait for a forecast that does not recover the entry. OPERATIONAL: stop broken by /0.90%. HONEST QUALIFIER -- the LIVE engine stop is and the close sits ABOVE it; this exit rests on the CARRIED written stop under never-lower-a-stop, not on today's row. 09-09 entry named QQQ 'the next name likely to break'. L2 NOT claimed (12wk +6.64% positive). COUNTERWEIGHT: Oracle +7% AH -- L8 gap-reprice if open gaps >~1.5%. Valuation blind (NA_ETF). ADR-0019: unreconciled (JSON). · news |
| XLK | Tech Select Sector SPDR | 185.22 | SELL ALL | 185.22 | 186.59 | 185.57 (+0.2%) | 186.37 (+0.6%) | 197.61 (+6.7%) | Closing the tech-sector position because the signal went to zero and the stop broke on the same session. XLK closed, below the stop set last session, while the model dropped it from BUY to outright NO TRADE -- a 69-point conviction collapse in one day, with momentum the weakest on the board. Tech was hit hardest by the move to a 4.91% ten-year and ~69% odds of a Fed HIKE next week, and the model's four-week forecast now sits below our cost. The bull counterpoint is real and worth naming: Oracle, an XLK holding, beat and jumped ~7% after the close -- but at a low-single-digit index weight that is worth roughly 0.2% on the ETF, an order of magnitude less than the damage already done. Take the loss. OPERATIONAL: stop broken by /0.73%; trail 75>85>69>0; Pillar_Consensus Conflicted, Exit_Strategy 'none' (no stop left to trail). L2 NOT claimed (12wk +6.69% positive). G1/G2/G3 N/A -- stop-break contrast case, not a divergence trim on an uptrend. L8 gap-reprice if open gaps >~1.5%. Valuation blind (NA_ETF). ADR-0019: unreconciled (JSON). · news |
| MAGS | Roundhill Magnificent Seven ETF | 69.18 | HOLD | 69.18 | 68.86 | 69.52 (+0.5%) | 70.27 (+1.6%) | 76.75 (+10.9%) | Holding the last equity position in the book. MAGS was the best relative performer on a day when names fell, down only 0.20%, and its trend reading is among the strongest on the board -- the megacap complex is absorbing the rate shock better than the AI, cloud and semi baskets being sold alongside it. It closed, still above the stop, so the discipline that is cutting three other positions today says keep this one. Headroom is thin and the next session decides it. OPERATIONAL: stop HELD at (no live engine stop on a cv0 row); close is only /0.46% above. Signal reverted to NO TRADE cv0 (Conflicted) after one BUY print, so the two-consecutive-NO-TRADE counter RESTARTS AT ONE. PRE-COMMITMENT for next EOD, unchanged: a second consecutive NO TRADE, or a close below, is the exit -- same test applied on 09-04/09-08. Trend 78 / Momentum 24. Valuation blind (NA_ETF). ADR-0019: unreconciled (JSON). · news |
| — | iShares Biotech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Passing on biotech despite it ranking first on the buy list. Two things stop it. The score lands at 64 against a 65 threshold -- a one-point miss, which is a miss. And the trade the model prints is not the pullback it claims to be: the suggested entry of sits 3.87% ABOVE the close, so buying it means paying up into a falling tape rather than waiting for weakness. The forward view is flat besides -- the twelve-week estimate of is under 2% above today's price. Nothing here justifies committing cash on a fourth consecutive down day six sessions before a Fed meeting priced at ~69% odds of a hike. OPERATIONAL: adj 64 = cv62 + val_adj 0 + PullbackBuy_VWAP bias +2. Entry_Distance_ATR +2.02 = chase geometry, declined on the no-chase rule even if it had cleared (Systemic 4 -- both buy-pool names mispriced above market this session). SE-2 inverted/flat horizon. RE-ARM TRIGGER: a genuine below-close PullbackBuy_VWAP limit with adj conviction >=65. Ledgered direction=none/optional for counterfactual grading. Valuation blind (NA_ETF). |
Outcome & track record
Accuracy at the time of this record.
48 Graded decisions Past recommendations old enough to score against what actually happened (target hit / stopped out / closed). This is the evidence base — the bigger the number, the more history behind the calls. Click to inspect every one. See the decisions →
-0.098 1-week calibration How much of the eventual 4-week move typically shows up in the first week (0 = almost none, 1 = most of it). Use it to read the 1-week estimates: a low number means prices drift toward the target slowly, so don't over-read a soft week-1.
50 Published records How many dated end-of-day verdicts exist for this book — the length of the public track record you can browse in the Archive below.