US End-of-Day Verdict 18 Aug 2026, 16:00:00 GMT-4

Sector ETFs — End-of-Day Verdict

NO ACTION - 0 ACQUIRE, 0 DISPOSE, 0 ANTICIPATE - plus 1 MANDATED WITHDRAWAL (UFO). Six names cleared the conviction floor, the widest bullish board in five weeks, and not one cleared the economics bar the book itself used to admit UFO a session earlier. The three highest-conviction prints are all the SAME trade - the Moderna/Merck melanoma readout (healthcare +3.5%, best day since April 2025, record sector high) plus the Treasury's expanded 10-30y buyback (gold to a two-month high) - bought after it happened: XLV (adj 90) closed AT its 52-week high with RSI 75.4, 1.39 ATR past a buy-stop the market has already run through, and its own Est_12W sits 2.09% BELOW the close (SE-2 on both legs) = 0.15x at the real price; IBB (adj 82) closed AT its 52-week high with RSI 80.4 after +6.58%, risking 12.75% to make 1.69% = 0.13x; GLD (adj 83) has a NEGATIVE four-week estimate (vs a close). XLF (adj 66) is the honest near-miss - best economics on the board at 1.57x with a genuine 1.16-ATR stop and the L1-favoured PullbackBuy_VWAP family, three of four written re-arm legs now PASS, and it is declined on leg 3 alone (entry = the close exactly), with Est_12W below entry for a third session. XLP (adj 83, first STRONG BUY of the run, SE-2 clear for the first time) is declined a third time on a 0.64-ATR stop inside one ordinary session's range, on the family whose measured stop_first is 0.667. XLY has the best-BUILT order in the book (1.07-ATR stop, no chase) and is still declined on a negative Est_4W. SOXX prints the highest-conviction BEARISH read in the book (FailedBreakout_Down_20D, conv 71, -2.21%, Est_12W -5.78%) with SMH collapsing -> 42 in two sessions - the rotation read the gauge exists to produce, with NVIDIA six sessions out. HONEST ACCOUNTING: yesterday's slot-ineligible decline on IBB at COST 7.23%; the same count rule saved 7.06% on SOXX and 6.4% on SMH - net roughly flat with enormous variance, and it demonstrably cannot distinguish a noise flip from a catalyst ignition (systemic finding #2).

Latest & archive All books

Recommendations

0 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
XBI	SPDR S&P Biotech ETF	169.55	WATCH	169.55	160.10	168.99 (-0.3%)	171.52 (+1.2%)	175.50 (+3.5%)	Biotech jumped 5.9% to a fresh 52-week high on the Moderna/Merck trial win; if this position is held it is a clear hold, not a trim - the gain is not yet large enough to trigger our profit-taking rule, no deterioration warning has printed, and the one-year outlook is still above today's price. We are raising the protective stop to lock in more of the move. Detail: BRANCH-CONDITIONAL - portfolio JSON shows (ground truth = FLAT, 08-07 card effectively SKIPPED); on the instructed branch @. On that branch: + / +8.70% = in one session; gain 2.87 ATR, just UNDER the 3.00-ATR arm threshold, Exit_Warning blank, so ADR-0012 cannot arm and no tick can fire. Est_12W = +3.51% above the close, so L2 does not fire. Close is / 8.6% clear of the stop. The AVOID/ReversalDown_Overbought print resolves to [HOLD] in Signal_Rationale and its Action_Rationale reads 'Flat; do not open (long-only)' - a don't-buy-here print, not a sell; pillars remain constructive (Trend 89, EMA20>EMA50>EMA200). TRAIL-RAISE -> (close - 2.0x ATR), closing basis, never widened; the model's Stop_Price is a short-side level and is discarded. FOUR ADR-0019 cards still need a human: trade buy/skip for 07-30 IBB, 08-06 IBB, 08-07 XBI, and trade skip AIQ 08-07. · news

Outcome & track record

Accuracy at the time of this record.

30 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.

Earlier record 18 August 2026 1 ACQUIRE (QUEUED), 0 DISPOSE, 0 ANTICIPATE. The book places its first order since the XLF withdrawal, on a trigger it wrote down in advance and did not move: UFO GTC BUY LIMIT @, stop, expires 08-21. Est_4W +6.20% vs a 2.98% stop = 2.08x, the only better-than-2x payoff on the board, and SE-2 does not fire for the first time in weeks. The tape was a textbook rotation out of AI into defensives - Nasdaq -1.3%, SOXX -4.96%, SMH -4.09%, XLK -2.47% against XLE +1.76%, XLV +1.60%, XLP +1.06% - on a WSJ report that nine top tech companies carry trillion of off-balance-sheet AI commitments, with the 30-year Treasury at a 19-year high. XLP (adj 73, Buy_Rank 1) is declined on the same written gate that declined XLK one session before it fell 2.47%: entry = close, 0.50-ATR stop, and a four-week estimate of +0.01%. XBI (conv 93, the book's highest) and IBB are both SLOT-INELIGIBLE at 1-of-3 anticipate prints and would fail on economics regardless. XLE has flipped outright bearish (ReversalDown_Overbought, RSI 72.9, three cents off its 52-week high), closing out six sessions of declines correctly. Later record 20 August 2026 NO ACTION - 0 ACQUIRE, 0 DISPOSE, 0 ANTICIPATE. The board collapsed and the doctrine got its report card in one session: of the six names that cleared the floor yesterday and were all declined, FOUR fell today (XLV -1.87%, IBB -2.83%, XLP -1.41%, XLY -1.61%), the near-miss XLF fell -0.92%, and only GLD rose (+0.34%) - a median -1.41% withheld in a single session. The bullish pool went from six names to TWO and nine funds print conviction zero. Both survivors are declined for OPPOSITE reasons, which is systemic finding #-19 made concrete: GLD has the conviction (100, the engine maximum) and fails its own forward arithmetic (Est_4W BELOW the close, 3.11-ATR stop, 1.12x twelve-week payoff collectable only THROUGH a negative four-week window and Jackson Hole); IBB has the best-constructed order this book has seen in a month (PullbackBuy_VWAP limit below the 20-day EMA, 1.16-ATR stop, 2.69x four-week payoff, SE-2 clear on both legs, both re-arm legs PASSED) and fails by three points of conviction. Anticipate slot empty for a 13th session on the count - not one ANT print in the last two snapshots. Book flat; XBI hold-pending on the unresolved 08-07 branch with the stop held at (low, no breach; chandelier is lower, never widen).