Recommendations
1 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 |
|---|---|---|---|---|---|---|---|---|---|
| MAGS | Roundhill Magnificent Seven ETF | 68.74 | BUY | 69.07 | 68.61 | 69.49 (+0.6%) | 69.89 (+1.2%) | 75.76 (+9.7%) | Buy the Magnificent Seven basket. MAGS was one of only five names on a 22-ETF board to close green on a session where a hawkish Jackson Hole keynote from Chair Warsh pushed September rate-hike odds to 57% and knocked semiconductors down more than 3% — relative strength earned against a hostile tape, not with it. The signal has strengthened four sessions running (WATCH → BUY 75 → STRONG BUY 85), it is the board's only STRONG BUY and its top-ranked buy, the moving-average ladder is fully stacked and the forward view is intact rather than inverted — the model sees roughly +10% over twelve weeks. The honest caveat is that the wider 2026 story runs the other way: the Mag-7 basket lagged the S&P badly through the first half and Goldman reads institutional flow as rotating out of megacap tech into semis, so this is sized and timed as a swing, not a position. OPS: STRONG BUY 85, adj 83 after the -2 FailedBreakdown family haircut. At-market (range -), stop. = — model was 85.49% x x 20% = but max_position_pct 60% is applied against the DECLARED capital, not the inherited phantom equity (systemic finding 3, 2026-08-27), which caps it at Defined risk 434 x = = 0.40% of book. PRINCIPAL WEAKNESS, stated plainly: the stop is 0.50 ATR = 0.67% below entry — inside one normal session's noise, and this book has declined names on exactly that ground before (SKYY 07-30 at 0.58 ATR, DIA 07-31 at 0.74 ATR). It is taken anyway because the 0.50-ATR stop is a hardcoded family constant today, not a name-specific artefact (systemic finding 3 this run), and MAGS clears every other gate. SE-2 does NOT fire: Est_12W > Est_4W > close. Payoff 1.78x on Est_4W. 1wk estimate carries the SE-3 low-reliability flag (calib_1w -0.08); the f=0.30 fallback gives vs the model's — same neighbourhood. Executes at the 2026-08-31 open; reprice if it gaps >1.5%. VOID if the open gaps below. · news |
| — | Financial Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Financials print a buy and rank second on the board — banks were among the handful of green sectors as Warsh's hawkish keynote steepened rate expectations — but the trade is declined on its forward view. The model sees the fund essentially flat twelve weeks out (+0.4%) while projecting +1.8% at four weeks, an inverted horizon that on this book means a short tactical swing at best, and the apparent 3.8x reward-to-risk is manufactured entirely by a stop sitting less than half a percent below the entry. Not enough forward reward to commit capital that MAGS uses better. OPS: BUY 75, adj 73 (bias -2), Buy_Rank 2. Trail SBUY 88 → SBUY 78 → BUY 66 → BUY 75, re-strengthening. Entry = close, stop = 0.49 ATR = 0.48%. SE-2 FIRES: Est_12W < Est_4W. RE-ARM: take it if Est_12W lifts back above Est_4W with conviction ≥70, or on a genuine below-close pullback limit ≥1.0 ATR wide. NOTE: this is the name the 08-26 card queued at and the 08-27 card recorded as FILLED on the tape (08-27 low). That fill was never written to input/sectoretfportfolio.json, the monitor now reports XLF as an exit, and this run therefore reverts to the JSON-literal branch: the book is FLAT with See ADR-0019 below. |
| — | First Trust Cloud Computing ETF | — | NO ACTION | — | — | n/a | n/a | n/a | The closest call on the board and the best risk/reward among the names that were declined. Cloud software is in a genuine uptrend — fully stacked moving averages, the only Trending regime among the buy candidates, and a model view roughly +8% over twelve weeks — but it gave back 0.9% into Friday's hawkish repricing and the trade would mean buying same-session weakness with a stop barely more than one percent away. Wait for the tape to settle. OPS: BUY 69, adj 67 (bias -2), Buy_Rank 4. Payoff 2.15x Est_4W, the best on the board; non-inverted forward; RSI 65.7, not extended. Stop = 0.50 ATR = 1.16%. Yesterday's re-arm trigger was 'AND Entry_Price within 1.0 ATR of close' — the second leg is now met (Entry_Price == close) but the first is not. RE-ARM: take it on a close near -162 that still prints conviction ≥69, or on any print where the stop widens past 1.0 ATR. |
| — | Invesco QQQ (Nasdaq-100) | — | NO ACTION | — | — | n/a | n/a | n/a | The Nasdaq-100 tracker prints a buy but it is a buy into the teeth of the selloff it just suffered. QQQ closed down 0.6% as rate-hike odds jumped to 57%, and the model's stop sits 0.6% below the entry — inside a single session's normal range on a wrong-side-of-the-tape entry. The twelve-week view is good (+8%); the next few days are not the moment. OPS: BUY 69, adj 67 (bias -2), Buy_Rank 3. Payoff 1.53x Est_4W, non-inverted forward (Est_12W > Est_4W > close). Stop = 0.50 ATR. RSI 51.9, Ranging regime. RE-ARM: a green close that holds above EMA20, or a pullback limit ≥1.0 ATR below the close. |
| — | Tech Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Declined on reward, not on trend. Tech closed down 1.6% and the model's own four-week estimate lands barely a quarter of a percent above the entry price — for the risk taken, there is almost nothing to win over the horizon that matters. OPS: BUY 69, adj 67 (bias -2), Buy_Rank 5. Payoff 0.25x on Est_4W vs entry — the worst payoff among the above-floor names and the purest instance of the flat-forward problem on this board. Forward is non-inverted at twelve weeks (Est_12W, +5.6%) but the four-week leg is dead. Stop = 0.50 ATR. |
| — | SPDR S&P 500 ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Two points short of the action threshold once the signal-family discount is applied. The broad index fell 0.2% on the Warsh reaction and the entry is simply the closing price, so there is nothing to wait for and nothing to queue below the market. OPS: BUY 66 → adj 64, under the 65 floor on the -2 FailedBreakdown haircut alone. Buy_Rank 6. Payoff 1.57x Est_4W — it clears the reward bar and fails only on conviction. Stop = 0.50 ATR. Non-inverted forward (Est_12W, +2.9%). RE-ARM: any print at conviction ≥67 makes it actionable. |
| — | Consumer Discretionary SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | The day's best performer on the board — consumer discretionary rose 1.2% while tech and semis were sold — but it lands two points under the action threshold after the signal-family discount. Worth watching if the rotation into cyclicals has legs. OPS: BUY 65 → adj 63, below floor. Buy_Rank 7. Trail WATCH → 52 → BUY 65 — first buy label in four sessions. Est_12W (+8.5%) is the strongest twelve-week read on the board. Price is pinned to EMA20/50/200 within a percent — no trend to lean on yet. RE-ARM: a second consecutive buy print with conviction ≥70. |
| — | Health Care Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Healthcare is the only name on the board printing the preferred pullback-to-VWAP setup, and it is the only one with a properly sized stop — but conviction is three points short and the model's twelve-week view is actually BELOW today's price. A cheap entry into a fund the model expects to be lower next quarter is not a trade. OPS: BUY 62, adj 62 (PullbackBuy_VWAP bias +0), Buy_Rank 8, below the 65 floor. Entry = 0.94 ATR below the close — genuinely queueable, and the stop is 1.16 ATR, clearing the width test every FailedBreakdown row fails today. DEAD FORWARD: Est_12W < close (-2.7%). RE-ARM: take it the moment Est_12W turns positive vs the close AND conviction reaches 65 — this is the highest-quality setup geometry on the board and only the forward view is stopping it. |
| — | Global X AI & Tech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Yesterday's near-miss on chase grounds has resolved itself — the AI/tech fund gave back 0.5% and the signal collapsed from a strong buy to a watch in a single session, vindicating the decision not to buy it one cent off the session high. OPS: STRONG BUY 85 → WATCH 62, a 23-point conviction collapse. Below floor. Est_12W (+7.6%) keeps it on the watchlist. RE-ARM on a fresh buy print with a queueable below-close entry. |
| — | SPDR Dow Jones Industrial Avg | — | NO ACTION | — | — | n/a | n/a | n/a | The Dow tracker was the market's most resilient major index on Friday, essentially unchanged while the S&P and Nasdaq fell — but the signal cooled back to a watch and there is no actionable print. OPS: WATCH 61, below floor. Trail WATCH → BUY 70 → WATCH 61. Entry_Price == close, nothing queueable. Est_12W (+1.9%) is a thin twelve-week case. |
| — | iShares Russell 2000 ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Small caps fell 1.4%, the second-worst of the broad indices, and remain a watch. Higher-for-longer rate expectations are a direct headwind to the most leveraged part of the market. OPS: WATCH 44, well below floor. Trail →. RSI 45.3, price below EMA20 and EMA50. Est_4W is BELOW the close. |
| — | Defiance Quantum ETF | — | NO ACTION | — | — | n/a | n/a | n/a | The quantum-computing basket fell 1.8% and lost its signal entirely after four sessions of watch prints. OPS: NO TRADE cv0, down from WATCH 64. Close broke below EMA20 and EMA50. Est_12W (+8.7%) is attractive but there is no entry to act on. |
| — | Consumer Staples SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Consumer staples rose 0.4% — the classic defensive bid on a hawkish day — but conviction is far below the threshold and the model's four-week estimate sits below today's price. OPS: WATCH 51, below floor. Est_4W < close. Flat-to-nothing forward; the defensive bid is a market signal, not a trade here. |
| — | SPDR Gold Shares ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Gold fell 3.2% as Warsh's hawkish message lifted real-rate expectations, and the signal engine has no read on it. Notably, the long-running cost of having declined this name has now collapsed: the streak opened 2026-08-08 at and peaked at +6.1% forgone on 08-27; after today's drop to it is +2.6%. OPS: NO TRADE cv0, 'Consensus conflict + low conviction'. Est_4W is 2.6% BELOW the close — the forward leg fails outright. Still declined; the decline is now cheap. |
| — | VanEck Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Semiconductors fell 3.5% — the worst name on the board — and the engine prints nothing at all, a day after printing an AVOID label on a +3.1% session. This book's semiconductor read has been uninformative across the entire NVDA reaction and its unwind. OPS: NO TRADE cv0. Close broke below both EMA20 and EMA50. Est_12W < Est_4W — inverted. See systemic finding 4. |
| — | iShares Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | The other semiconductor proxy, down 3.2%, and silent for a fifth consecutive session — cv0 through the entire NVDA run-up, the reaction and now the unwind. OPS: NO TRADE cv0. Est_12W is BELOW the close. RSI 43.1 and price under EMA20/EMA50. |
| — | SPDR S&P Biotech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Biotech fell 3.5% on the rate repricing — long-duration equity is the most rate-sensitive corner of the market and it traded like it. No signal. OPS: NO TRADE cv0 for a third straight session. Close held just above EMA20. Est_12W (+5.2%) keeps it on the watchlist. |
| — | iShares Biotech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Large-cap biotech fell 2.7%, no signal. The BUY - ANTICIPATE print from four sessions ago has fully lapsed — three consecutive NO TRADE prints since — so the anticipate slot has nothing eligible today. OPS: NO TRADE cv0. Est_12W (+4.4%). The 08-06 gap-guard card remains open under ADR-0019. |
| — | Destiny Tech100 Inc | — | NO ACTION | — | — | n/a | n/a | n/a | The book's only priced name on fair value, and the only one carrying a valuation penalty. Fell 1.9% and reverted to no signal after a single buy print. OPS: NO TRADE cv0. OVERVALUED_VS_RI, MoS -0.78 → val_adj -4 (residual-income basis; the fair-value file is 79 days old). Close against a anchored VWAP — still stretched. High-volatility, wide-band name; the model's 4wk band spans -. |
| — | Industrial Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Industrials fell 0.9% and remain the board's weakest momentum reading. No signal. OPS: NO TRADE cv0 for a fourth straight session. RSI 37.8 — the lowest on the board — with price below EMA20 and EMA50. Est_4W < close. |
| — | Procure Space ETF (SpaceTech) | — | NO ACTION | — | — | n/a | n/a | n/a | Space fell 1.9% and continues to print an avoid label. Long-only book, so this costs nothing directly, but the read is negative. OPS: AVOID 48 on FailedBreakout_Down_20D, fourth consecutive avoid print. RSI 37.0, price below EMA20/EMA50/EMA200 — the only name on the board under all three. No target price printed. |
Outcome & track record
Accuracy at the time of this record.
35 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 →
-0.080 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.