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 |
|---|---|---|---|---|---|---|---|---|---|
| DELL | Dell Technologies Inc | 439.34 | HOLD | — | 423.45 | n/a | 502.89 | 626.06 | Keep the full Dell position and lift the stop again - after two big up-days the AI-hardware tape cooled and Dell eased 0.6% to 439.34, but the bull case is intact. Dell's AI-server momentum is holding: AI orders last quarter, FY27 AI-optimized server revenue guided (+144%), non-GAAP EPS (+74% YoY), and Wall Street sits at a consensus with 0 Sells - the only debate is margin mix (gross margin 17.8% vs a legacy 21.1%), which caps the multiple but is not a demand crack. The position is back to roughly break-even on our 439.41 cost, conviction eased but the signal is still the bullish FailedBreakdown family and the 12-week view of 626.06 sits ~42% above the price - a winner to hold, not to trim. OPERATIONAL: no exit arms (no stop break, 12wk strongly positive, no PROFIT_ARMED); the -15pt conviction ease is below the 20pt collapse tick and the name is not armed. RAISE stop 413..45 (model stop, ratchet up only, never down; ~0.50 ATR / 3.6% below close). Escalation = a decisive close below ~407.6 (423.45 - 0.5xATR), a 12wk flip negative, or 2 consecutive NO TRADE arms the L2 exit. UT-10: NO ADD - do not pyramid a fully-recovered name. 12wk 626.06 exceeds the DCF anchor (growth beyond priced-in); 4wk model target 502.89; 1wk n/a (HOLD, no actionable entry); model band 400.37-474.35. L1/L4/L8, UT-10 applied. · news |
| TSM | Taiwan Semiconductor Manufacturing | 415.58 | HOLD | — | 406.37 | n/a | n/a | 399.05 | Hold the residual half of TSMC on its 406.37 stop - the bearish read collapsed to neutral rather than completing into an exit. After yesterday's 0.8% slip the shares fell another 1.3% to 415.58, and the engine's signal went from a bearish AVOID (conviction 49) to a flat NO TRADE (conviction 0, 'consensus conflict + low conviction'). The 12-week view (399.05) is still ~4% below the price, so the position stays correctly de-risked at half size - but our rule to complete the exit needs a decisive break of the 406.37 stop AND a negative 12wk, and the stop is not broken (price is 2.3% above it); a single NO TRADE print with the stop intact is not a completion basis. We let the residual work rather than sell into weakness. Q2 was a record ( revenue, EPS +74.5% YoY) but the capex raise to -64B plus the Arizona expansion is the margin/AI-spend overhang the tape keeps discounting - neutral, no override; the CEO sees AI demand through 2029-30. OPERATIONAL: L2 re-tested - only the negative-12wk leg holds, the stop-break leg does not -> no completion; not 2 consecutive NO TRADE. G2 SUPPRESSES the valuation amplify (DCF vs price ~9x broken) so the MoS -14.43 is val-blind. UT-9: PROFIT_ARMED (T12_Progress 104.14) on a -5.12% underwater position (Gain_ATR -1.47) = arm-on-loss mislabel, inert. Keep stop 406.37 (ratchet); a decisive close below it with a still-negative 12wk completes the exit. L2/L4/L5/L6/L8, UT-9 applied. · news |
| TSLA | Tesla Inc | 319.69 | NO ACTION | 319.69 | 250.57 | 339.41 (+6.2%) | 385.42 (+20.6%) | 228.09 (-28.7%) | Tesla was the loudest buy signal on the board today - a STRONG BUY at conviction 85, top of the ranking, with a clean risk-defined entry right at the 319.69 close and a deeply oversold RSI of 29 - and we still passed, correctly. Three things block it. First, it fails our quality screen outright (F-Score/FCF gate reads FALSE), which hard-blocks a new entry regardless of how loud the signal is. Second, and decisively, the model's own 12-week projection is 228.09 - roughly 29% BELOW the entry price - so the 'STRONG BUY' is an oversold-bounce call fighting a bearish forward view, not a trend we want to own. Third, it is a one-snapshot flip (three AVOID prints then a sudden STRONG BUY), which is low-stability. A bounce trade against the book's rules, not an investment. Watch it only if the 12-week view turns positive AND the quality inputs improve. OPERATIONAL: ledgered direction:none / optional:true so the counterfactual grader prices what the quality-gate + negative-12wk block cost; val_adj -10 (MoS -17.86) would leave adj 75 absent the hard gate; 1wk shown at f=0.30 per L5. L1 (no reversal chase into a bearish 12wk) applied. |
Outcome & track record
Accuracy at the time of this record.
9 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.
24 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.