Recommendations
1 to acquire · 1 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 |
|---|---|---|---|---|---|---|---|---|---|
| DELL | Dell Technologies Inc | 467.27 | ADD — QUEUED @465.04 | 465.04 | 390.11 | 525.69 (+13.0%) | 667.22 (+43.5%) | 639.35 (+37.5%) | Dell broke to a fresh 52-week high on the back of an AI-server business that is now the whole story: last quarter's revenue grew 88% year on year, the company booked 4bn of AI orders, and management lifted its full-year revenue guidance to -169bn and its AI-server target to about $60bn. The model's read is the strongest this book has produced - a 52-week breakout at conviction 88, ranked first, with trend and momentum both near maximum - and the holding has just turned profitable for the first time since it was opened in July. We are adding to a winner we already own, at the model's own trigger price, with the risk line defined. The valuation screen is the one thing pushing back: on an earnings-power basis the shares look richly priced, which is why the add is deliberately half the size the signal alone would justify. Operational nuance: ADD path (112.34% x 347 =) x 0.5 size modifier (MoS_FV -3.14, <= -3 tier) =; GTC buy-stop at the printed Entry_Price 465.04 (ED -0.06, so it fills on the open unless DELL gaps below the trigger - that is the intended protection). Post-fill @ blended 448.63 = 25.3% of book, max_position_pct 60% not binding. L6 tested and does NOT bind: +8.92% is sector beta (SOX +6%, S&P record close, PLTR +30%), not a post-earnings gap - Dell last reported FQ1 2027 on 2026-05-28 and next reports late August. L1 overshoot flag: Target_Price 667.22 and even the f=0.30 1wk of 525.69 print ABOVE the model's own Est band top of 509.17; treat 509.17 as the credible 4-week ceiling. 12wk 639.35 exceeds the DCF anchor 485.61. UT-10 examined not merely cited: its not-underwater gate now passes ( +6.34%, Gain_ATR +0.70) while its non-spiking-ATR gate fails (ATR 29.22->39.77), and its stated scope is pullback-pyramiding, so it discounts size rather than vetoing. RSI_DIV on the row is neutralised as a trim trigger by G1 (fresh BreakoutUp at conv >= 80) and is a trail instruction, not a buy blocker. STOP RATCHET: the engine stop LOWERED 390.11 -> 385.49 on an up day (ATR expansion outran the anchor); stop is held at 390.11 and must never be lowered. Tighten on 08-07 NFP and 08-12 CPI (horizon stance tighten-trail). · news |
| TSM | Taiwan Semiconductor Manufacturing C | 417.17 | SELL ALL | 417.17 | 382.61 | n/a | n/a | 373.84 (-10.4%) | Closing out the last of a TSMC position that has been wound down since mid-July, at a small loss. The business itself is in excellent shape - Q2 revenue of 2bn at a 67.7% gross margin, next-quarter guidance up 37% year on year, capex raised to -64bn on customer demand, and price rises of 5-10% going through on leading-edge chips - but none of that is a trading signal. The model now flags this as a failed breakout with a strong sell reading and ranks it the single best sale in the book, and its own twelve-week view still sits about 10% below today's price. Holding the remainder of a losing position in a name the model has no upward case for, while the same book has a high-conviction use for the cash, is not a decision worth defending. If TSMC deserves owning from here it deserves a fresh entry on a fresh signal. Operational nuance: 8th arming (07-25/28/29/30/31, 08-01, 08-04, today), all unfilled - executor stall, 9th session - so this is UT-11 re-fire, not re-litigation. Engine Action_Rationale itself reads 'REDUCE 90% (target full exit)', so 100% is the model's own portion. The L2 stop-break leg is RETIRED (close 417.17 is now +2.66% ABOVE the old 406.37 stop); the neg-12wk leg holds at -10.39%; the fresh STRONG SELL - REDUCE conv 69 / Sell_Rank #1 / Exit_Strategy immediate is a stronger origination than either. Disclosed against the exit: close is now ABOVE both EMA20 411.69 and EMA50 414.63 and RSI has recovered to 51.06 - price action is improving, the forward view has not. Written withdrawal trigger tested at required consecutive closes above 406.37 and RETIRED as superseded (no stale exit left to cancel). PROFIT_ARMED is the UT-9 arm-on-loss mislabel (Gain_ATR -1.21), inert, ~20th session. Valuation amplify suppressed by G2 (DCF 45.15 vs price 417.17, ~9.2x off), 16th session. Proceeds; realised ~- (-4.76% vs 438.02 cost). Est band 375.00-425.51 - top is only +2.0% above the exit, floor -10.1%. Re-entry condition: BUY/STRONG BUY conv >= 65 with a live Entry_Price and Target_12Week ABOVE entry. · news |
| SNOW | Snowflake Inc. | 316.77 | NO ACTION | 318.98 | 267.55 | 349.84 (+9.7%) | 421.85 (+32.2%) | 451.40 (+41.5%) | Snowflake keeps flashing a buy and we keep declining it, for the tenth session running. The trend is genuinely strong, but the company fails our quality screen outright - weak fundamental scoring and negative earning power on the current business - and the shares are now stretched after a 12% run in five sessions, so buying here would mean paying up for a name we would not own on the fundamentals. Operational nuance: blocked three independent ways. (1) MoS_FV -1.82 -> val_adj -9 -> adj, nine below the 65 floor. (2) Quality_Pass FALSE (F-Score 5, EPV -/sh, rank 23/31) hard-gates the new entry. (3) RSI 77.11 and VWAP distance +13.58% with a buy-stop at 318.98 ABOVE the 316.77 close (ED +0.13) fail the no-chase rule. UT-12 also folds MomentumContinuation_Up into L1's discount list (own cell n=2, 0/2 on 1wk). Ledgered as a counterfactual so the ten-session cumulative cost of the quality gate in this book becomes priceable (UT-12 advisory d-iii). Sizing shown is hypothetical: @ 318.98 12wk 451.40 exceeds the DCF anchor 112.27. |
| GOOGL | Alphabet, Inc.- Class A | 377.65 | BUY-STOP | 378.15 | 334.45 | 404.37 (+6.9%) | 465.54 (+23.1%) | 365.19 (-3.4%) | Alphabet set up an early-entry signal today - the first real candidate for the book's anticipation slot in thirteen sessions - and it is still declined. It needs to show the same setup on consecutive days before we act on it, it fails our quality screen, and the model's own twelve-week projection puts the shares slightly below today's price, which is a poor combination for opening a new position. Worth watching: another print tomorrow makes it a live candidate on stability, though the other two objections would remain. Operational nuance: refused on three counts. (1) The anticipate slot requires BUY - ANTICIPATE in >= 2 of the last 3 snapshots; GOOGL printed AVOID(73) -> AVOID(67) -> ANTICIPATE(77) =. (2) Quality_Pass FALSE (F-Score 5, rank 18/31) hard-gates a new entry regardless of the slot. (3) Target_12Week 365.19 vs a 377.65 close = -3.3%, a negative forward view on a bullish label. Adjusted conviction is 77 + (-4) = 73, comfortably above the 65 floor, so this is a gate/stability refusal, not a conviction one. The 2026-07-05 overlay override on GOOGL (invalidated when close below 345) is live and NOT invalidated, but an override cannot repair a failed gate. Ledgered as a counterfactual alongside SNOW so the quality gate's cost becomes priceable. |
Outcome & track record
Accuracy at the time of this record.
12 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 →
0.134 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.