This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.

US End-of-Day Verdict 8 Sept 2026, 16:00:00 GMT-4

US Tech — End-of-Day Verdict

NO ACTION (0 acquire / 0 anticipate / 0 dispose)

Recommendations

0 to acquire · 0 to dispose

TickerNameCloseActionAction 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
CRWVCoreWeave, Inc.99.83NO ACTION99.8392.88103.96 (+4.1%)113.61 (+13.8%)93.29 (-6.6%)CoreWeave flipped from four sessions of AVOID to a conviction-82 BUY at rank 2 on a $129bn contracted backlog and 112% revenue growth, but the fundamental screen fails outright: F-Score 4 and free cash flow of minus 6bn (FCF yield -11.5%). We do not open a new position in a company burning cash at that rate no matter how good the chart looks, and the 12-week model view is itself negative at 93.29 against a 99.83 close. Blocked as a new entry; recorded so the cost of the gate can be measured. ASSUMPTION STATED: CRWV prints Val_Signal=NA (no intrinsic anchor computable on negative FCF), which zeroes val_adj, but Quality_Pass=False was genuinely computed from real fundamentals - the NA carve-out switches off the valuation adjustment, not a quality screen that ran and failed. Re-arm trigger: Quality_Pass flips True on a fresh fairvalue fetch, or a positive Target_12Week with conviction >=80. · news
NBISNebius Group, N.V.243.88NO ACTION243.88234.32254.10 (+4.2%)277.96 (+14.0%)260.16 (+6.7%)Nebius printed the book's strongest signal of the day - a conviction-91 STRONG BUY at rank 1, straight out of two sessions of AVOID - on the back of its Goldman Communacopia appearance and a Citi price target raised to a Street-high The technical and news case are both strong. It is nonetheless blocked: the quality screen fails (F-Score 6 but free cash flow of minus 15bn) and the stock trades at roughly nine times our fair-value anchor, the deepest overvaluation in the buy pool. A cash-burning name priced for perfection is not where new money goes. Highest-conviction blocked name of the session; ledgered as a counterfactual to price what the gate costs (UT-12 advisory d-iii). Re-arm: Quality_Pass True. · news
SNDKSandisk Corporation1737.99NO ACTION1737.991685.681800.76 (+3.6%)1947.23 (+12.0%)1969.65 (+13.3%)Sandisk is the only buy candidate today that actually passes the fundamental quality screen (F-Score 7, positive free cash flow), but the conviction is not there: a raw 68 falls to 59 after the valuation haircut and the FailedBreakdown family's newly-actionable negative track record, six points short of the 65 bar. Third consecutive session declined, and the conviction is drifting down -> 68), not up. Re-arm trigger: raw conviction >=74 with the entry not extended, which would clear the floor at 65.
DELLDell Technologies Inc533.88HOLD538.31467.56n/a737.26 (+37.0%)760.78 (+41.3%)The book's anchor position and its only large winner, up 15.7% on a 533.88 close with a 12-week view of 760.78 - there is no case for touching it. Conviction eased but the name stays a HOLD in an intact uptrend, and it is not profit-armed (gain 2.19 ATR, below the 3.0 arm; 12-week progress 70%). Stop ratcheted 452.74 -> 467.56 on the 2.0x ATR chandelier, locking in roughly a further. Note the scan's own line printed 438.83, BELOW the existing stop - the ratchet never lowers, so it is ignored, same judgement call as 09-05.
MUMicron Technology, Inc.1000.26HOLD1000.26969.00n/a1090.06 (+9.0%)1133.87 (+13.4%)Yesterday's 30-share add filled at 1036.835 against a 1016.59 reference - a 2.0% gap through the L8 reprice guard - and the position now sits at a 988.9986 blended cost against a 1000.26 close, up 1.1%. Signal is a steady HOLD at 68 with a 12-week view of 1133.87, so the position stands. Stop held at 969.00: the scan's 977.81 line sits only 0.50 ATR under the close, inside a single day's noise on a 45-point-ATR name. TSMC August revenue 09-10, PPI 09-10 and CPI 09-11 all touch this name; FQ4 earnings 09-30 are still missing from the horizon file.
TSMTaiwan Semiconductor Manufacturing C439.00HOLD437.13419.45n/a502.38 (+14.9%)439.06 (+0.4%)Filled yesterday at 438.02 and already flat-to-green at a 439.00 close. The name still prints a strong conviction-83 line, but as BUY - ANTICIPATE rather than a live BUY, and it has only one anticipate print in the last three snapshots against the two required - so no add today, which also respects UT-10 (do not pyramid into a position opened one session ago). Stop set at 419.45, the level carried from the 09-05 acquire card: the scan's 404.50 is a 3.2 ATR line, too loose for a fresh position. TSMC August revenue lands 09-10, the trade's first real test.
CRMSalesForce Inc249.12NO ACTION249.12251.77n/a272.10 (+9.2%)355.00 (+42.5%)Salesforce closed 249.12, a hair below its 251.77 stop, and this is the one genuinely contestable call of the session. We hold. The breach is 1.05%, or 0.23 ATR - well inside the noise band and not a decisive break - and everything else is improving, not deteriorating: four sessions of NO TRADE resolved into a HOLD, the regime reads Trending, RSI is 67.5 and the 12-week view sits at 355.00, some 42% above the close. The stock is up roughly 34% in a month on strong Q2 numbers with a Dreamforce Investor Day catalyst on 09-16. Learning L2 requires a stop break AND a negative 12-week view to originate an exit; the second leg is absent, so this is not a sell. Stop held at 251.77 (the scan's 243.38 is a 0.50 ATR line). EXPLICIT EXIT TRIGGER, armed: a second consecutive close below 251.77, or any close below 245.99 (0.5 ATR under the stop), fires a DISPOSE next session without further debate. Ledgered optional so the counterfactual grader prices the decision not to cut here. · news
AAPLApple316.22HOLD316.22314.62n/a331.36 (+4.8%)325.23 (+2.8%)Apple's 'Surprise and Shine' event - iPhone 18 Pro plus the first foldable, and new CEO John Ternus's first keynote, called the most consequential iPhone launch in a decade - lands TODAY, on the execution date. The catalyst-aware rule is unambiguous: hold or trail through the event, never pre-trim into it. Position is 3.3% underwater at a 316.22 close. The PROFIT_ARMED flag on this row is an arm-on-loss mislabel and is inert - gain is MINUS 1.42 ATR, so no profit-take can fire (UT-9). Stop held at 314.62; flagging plainly that this is only 0.51% below the close, so an adverse event reaction very likely takes it out. That is accepted rather than papered over - widening a stop to survive a binary event is how risk lines stop meaning anything. · news
NVDANVIDIA Corporation225.73HOLD225.73215.95n/a241.49 (+7.0%)251.32 (+11.3%)Flat position, 0.5% below the 226.80 cost after the 09-04 trim, still a HOLD though conviction dropped - the sharpest single-session conviction decline in the book. That would be a fire tick under the profit-take rule, but the position is not armed (gain MINUS 0.14 ATR, 12-week progress 89.8%, just under the 90 threshold), so nothing fires. Stop held at 215.95; the scan's 221.79 is only 0.50 ATR under the close and would be noise-taken. Watch: the NBIS warrant lock-up on roughly 21M shares hits 09-11.
PLTRPalantir Technologies Inc.170.30HOLD176.70167.07n/a189.94 (+7.5%)231.21 (+30.8%)Bought four sessions ago at 175.81, now 3.1% underwater at a 170.30 close with conviction slipping. The weakest holding in the book and the one to watch, but nothing fires: still a HOLD, not armed, 12-week view 231.21 remains well above the close. No add either - the entry sits 0.72 ATR above the close and this book's PullbackBuy_VWAP cell is running at a 25% hit rate on six graded trades. Stop held at 167.07, 1.9% below the close.

Outcome & track record

Accuracy at the time of this record.

39 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 →
0.017 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.
53 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.

This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.