Recommendations
3 to acquire · 0 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 | 64.32 | BUY | 64.32 | 63.88 | 64.63 (+0.5%) | 64.86 (+0.8%) | 67.70 (+5.3%) | The AI trade split in two today and AIQ owns both halves, which is exactly why we want it: semiconductors surged (SOXX +3.5%, NVDA +2%, AMD +3%, Intel +4%) on Micron's plan to double AI memory output, while software and mega-cap tech sold off on a hot jobs report that pushed September rate-hike odds to ~60%. AIQ closed dead flat at +0.03% between those two forces and still printed the strongest buy signal on the board — highest conviction (90), top rank, and the only holding whose internal indicators are Mostly_Aligned rather than merely consolidating. Buying the intersection means we no longer have to guess which layer of the AI complex leads next. OPERATIONAL: at-market entry, Entry_Distance_ATR 0.00 so nothing to queue; =, 85.49 Portion of a 183.97 three-way split = 46.5% of (75% of post-fill cash). SE-1/L1: FailedBreakdown_Up_20D is the book's actionable-negative family, live bias -1 applied. SE-2 edge case: forward structure is monotonic but the 4wk drift is only +0.84% -- run to the Target_Price as a tactical swing, not a position hold. SE-3/L5: calib_1w -0.068 degenerate, 1wk estimate carries a low-reliability flag. Stop is just 0.50 ATR (-0.68%) -- inside daily noise, high stop-first probability, total risk. Valuation blind (NA_ETF, 86d stale). Re-arm/re-examine on a hot August CPI 09-11. · news |
| XLK | Technology Select Sector SPDR | 187.28 | BUY | 187.28 | 185.80 | 187.73 (+0.2%) | 189.57 (+1.2%) | 196.13 (+4.7%) | XLK is how we own today's actual leadership without buying an ETF our own engine has labelled AVOID. Chips led the market outright -- Intel +4%, AMD +3%, Nvidia +2% -- shrugging off a hot August payrolls print, and semiconductors are XLK's heaviest exposure, which is why it closed +0.70%, the best non-semi name on the board. Its signal is also the steadiest thing we have: two consecutive BUY prints at identical conviction 75, where every other candidate whipsawed. The counterweight is Apple, which fell on foldable production problems made worse by the same memory scarcity that lifted the chip names -- the story cuts both ways inside this fund. OPERATIONAL: at-market, Entry_Distance_ATR 0.00; =, Portion 49.24/183.97 = 26.8% of, rounded down to stay inside the allocation. Ranked ABOVE QQQ despite losing the Buy_Rank tie-break (3 vs 2) -- news re-ranks at the news step of the chain. SE-1 live bias -1 applied. SE-2 does not fire: 1wk < 4wk < 12wk monotonic. SE-3 low-reliability flag on the 1wk. Stop = 0.50 ATR (-0.79%), total risk; noise-tight, expect stop-first. Valuation blind (NA_ETF). PPI 09-10, CPI 09-11, FOMC 09-15 all inside the 4wk horizon. · news |
| QQQ | Invesco QQQ (Nasdaq-100) | 718.96 | BUY | 718.96 | 715.15 | 719.67 (+0.1%) | 730.77 (+1.6%) | 791.41 (+10.1%) | QQQ was the only broad index to close green today (+0.18%, against the S&P -0.4% and the Dow -0.5%) and it carries by far the strongest 12-week outlook on our board at +10.1% -- roughly double the next-best name. That combination is worth a small position even though its signal history is the choppiest of today's three buys, having flipped through a no-trade reading only two sessions ago. The clear risk is that QQQ is the purest interest-rate-sensitive holding we have, and the news that moved markets was a jobs report strong enough to put September rate-hike odds near 60% ahead of the Sept 15-16 Fed meeting. August CPI on Sept 11 can hurt this card more than the other two, so it gets the smallest allocation. OPERATIONAL: at-market, Entry_Distance_ATR 0.00; =, Portion 49.24/183.97 = 26.8% of -- a 7-share position is a rounding artefact of a share price against a small, not precision. Demoted below XLK at the news step despite winning the Buy_Rank tie-break. SE-1 live bias -1. SE-2 does not fire. SE-3: the +0.10% 1wk estimate is the model declaring no view -- low-reliability flag. Stop = 0.50 ATR (-0.53%), total risk. Valuation blind (NA_ETF). First card to re-examine on a hot CPI 09-11. · news |
| MAGS | Roundhill Magnificent Seven ETF | 69.44 | UNRECONCILED @69.82 | 69.82 | 66.21 | 70.78 (+1.4%) | 71.56 (+2.5%) | 78.44 (+12.3%) | Our buy order for MAGS almost certainly executed -- the fund traded down to, a clear 0.87% through our limit -- but the holdings file still shows no position, so the book cannot see it. This needs confirming either way. If we own it, hold: Tesla fell 6.4% on poor Cybercab reviews and Apple dropped on production problems, which is why MAGS closed -1.41% and why the signal has gone flat, but the close is comfortably above our stop and the 12-week outlook is still +11.4%, so neither exit test is met. An unrecorded position is an unstopped position -- that is the real risk here, not the price. OPERATIONAL: ADR-0019 disposition required -- 'trade buy sectoretf MAGS 179 69.82' or 'trade skip sectoretf MAGS'. L2 exit test explicitly NOT met (no stop break, 12wk strongly positive). Signal now NO TRADE cv0, Conflicted consensus: ONE such print is not an exit; a SECOND consecutive one makes it a sustained-NoTrade exit case per CLAUDE.md 9. Hold the stop meanwhile. 29th consecutive run with undispositioned cards on this human-managed book. · news |
| SKYY | First Trust Cloud Computing ETF | 161.56 | UNRECONCILED @162.51 | 162.51 | 159.15 | 162.61 (+0.1%) | 163.08 (+0.4%) | 169.42 (+4.3%) | Our cloud-software order looks to have filled -- SKYY traded to, 0.80% through the limit -- but no position is recorded. If we own it, hold it, and raise the stop to. The trade thesis was that falling interest rates favour long-duration software; August's blowout jobs report reversed that argument within 24 hours, rate-hike odds jumped to roughly 60%, and SKYY was the worst performer on the board at -1.44%. The signal is still a buy but has decayed sharply from a strong buy at 85 conviction to 66, so treat this as a tactical position on a weakened case rather than a core idea. OPERATIONAL: ADR-0019 disposition required -- 'trade buy sectoretf SKYY 76 162.51' or 'trade skip sectoretf SKYY'. Live Stop_Price is now, up from the recorded on 09-03 -- raise it. Adjusted conviction 67 clears the 65 floor so it is not a sell; it is simply no longer a top-3 idea (Buy_Rank 4). Four-print escalation 73/73/85 broken. PullbackBuy_VWAP bias +1 applied. · news |
| XLF | Financial Select Sector SPDR | 58.10 | UNRECONCILED @57.93 | 58.10 | 57.74 | 58.13 (+0.1%) | 58.28 (+0.3%) | 58.10 (+0.0%) | The financials order placed two sessions ago still has no disposition and this is now the longest-running gap in the book. It was a market order for that should have executed near on Sept 3; XLF has since given back -0.79% to close at. The signal remains a buy but only barely, at 65 after adjustment against a 65 threshold, and it ranks 6th, outside today's top three -- so it is neither re-recommended at the stale price nor abandoned. It simply needs to be recorded. OPERATIONAL: ADR-0019 -- 'trade buy sectoretf XLF 144 58.00' or 'trade skip sectoretf XLF'. Not re-queued at the stale (provenance rule); live Entry_Price is at market, live stop. Note the 12wk estimate equals the close exactly -- a flat forward view, SE-2 territory, which is a further reason it is not a top-3 card today. · news |
| — | Health Care Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Near-miss, 4th in line. Healthcare fell -1.04%, the third-worst name on the board, as the defensive bid that carried it through late August evaporated with the rate scare. Decisive point against it: the 12-week estimate of now sits BELOW the close, an inverted forward view -- the model is saying this is worth less in three months than today. Adjusted conviction 67 clears the floor but the forward structure does not. SE-2 inversion fires. |
| — | SPDR S&P 500 ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Sits exactly on the 65 action threshold after the family haircut, with no margin. The S&P closed -0.39% and broad index beta is already being bought today through QQQ, which carries a far stronger 12-week view (+10.1% vs SPY's +2.08%). No independent edge; declined. |
| — | SPDR S&P Biotech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | One point below the action threshold, and the direction of travel is what matters: conviction has decayed four sessions running, ->. Small-cap biotech is long-duration and was sold with the rest of it on the hot jobs print. Declined. |
| — | SPDR Dow Jones Industrial Avg | — | NO ACTION | — | — | n/a | n/a | n/a | Yesterday's one-print BUY at 77 conviction lasted exactly one session and has reverted to WATCH at 61, below the floor. The Dow was the worst major index today at -0.53%. Declined -- this is the whipsaw the stability rule exists to filter. |
| — | Destiny Tech100 Inc | — | NO ACTION | — | — | n/a | n/a | n/a | Rose +1.40% but the signal weakened to WATCH at 49 conviction, far below the floor. It is also the one name in this book the valuation model can actually price, and it reads OVERVALUED with a negative margin of safety (-0.78, val_adj -4) and a failed quality screen. Declined on both technicals and valuation. |
| — | VanEck Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- the engine printed a high-conviction BEARISH label (AVOID, conviction 86) on the day SMH closed +2.61% and led the board, so there is nothing to act on in a long-only book either way. Flagged as this run's headline engine-quality finding: a breakdown signal firing on a name making its best move in weeks, alongside the identical failure on SOXX. |
| — | iShares Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- bearish label (AVOID, conviction 76) on the single best performer on the board, +3.52%, driven by Micron doubling AI memory production and broad chip strength. Long-only, so nothing is actionable; logged as the second instance of the same misfire as SMH, same signal, same session. |
| — | Procure Space ETF (SpaceTech) | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- bearish signal in a long-only book. Fourth consecutive AVOID print, conviction decaying ->. |
| — | Consumer Discretionary SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- bearish signal, long-only. Consumer discretionary was the second-worst sector at -1.33%, dragged by Tesla's 6.4% fall on weak Cybercab reviews. |
| — | Energy Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- NO TRADE, consensus conflict with low conviction. Closed -0.87%. The strong-buy call of Sept 1 has now fully unwound. |
| — | Consumer Staples SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- NO TRADE, consensus conflict. Staples fell -0.80%; even the defensive bid did not hold. |
| — | Industrial Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- NO TRADE for a fourth consecutive session, consensus indeterminate. |
| — | Defiance Quantum ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- NO TRADE, consensus indeterminate, despite closing +1.21% alongside the chip complex. |
| — | iShares Russell 2000 ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- NO TRADE for a fourth consecutive session. Small caps managed only +0.28% on a day the rate-hike odds rose. |
| — | SPDR Gold Shares ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No action -- NO TRADE, consensus indeterminate. Gold fell -0.84% as yields spiked on the jobs report, the textbook reaction. |
Outcome & track record
Accuracy at the time of this record.
41 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 →
-0.068 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.