US — End-of-Day Verdict
DISPOSE: NVDA 88@196.93 (strong-sell x3 + neg-12wk) + GOOGL 30@367.03 (fired profit-take). ACQUIRE: LLY 15@1165.58 + SNOW 140@243.55 queued (exp 07-11) + AMD 14@~517 market. NET/DDOG/JPM quality-blocked. BAC anticipate quality-blocked. NBIS/KLAC/SNDK stop-breach holds. SPCX muted (Aug lock-up concern, manual stop 135).
Recommendations
3 to acquire · 2 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 |
|---|---|---|---|---|---|---|---|---|---|
| NVDA | NVIDIA Corporation | 196.93 | SELL 88.52% | 196.93 | 209.54⚠ | n/a | n/a | 169.43 (-14.0%) | Continue de-risking NVIDIA's residual stub: a stable STRONG SELL - REDUCE (3 prints cv69->76), a failed 20-day breakdown, and a negative 12-week view combine with a DeepSeek in-house-chip demand crack to make this a clean trend exit, not panic. L2/L3: stop-break+neg-12wk exit, execute the residual promptly. Sell 88, keep a 12-sh stub; trail 184.30. Proceeds. · news |
| GOOGL | Alphabet, Inc. Class A | 367.03 | SELL 30% | 367.03 | 345.00 | 373.32 (+1.7%) | 388.00 (+5.7%) | 356.75 (-2.8%) | Fired ADR-0012 profit-take: Alphabet is profit-armed and prints a dead forward view (12wk 356.75 below 1.02x the close), firing tick(c) for a 30% trim. Re-fires the 07-07 unexecuted 30-sh tick (L3). Overlay sanctions exactly and says trail the rest through 07-22 earnings. Keep 70, trail 345.00. Proceeds. |
| LLY | Eli Lilly & Co | 1235.56 | ADD — QUEUED @1165.58 | 1165.58 | 1180.30 | 1195.51 (+2.6%) | 1265.34 (+8.6%) | 1598.18 (+37.1%) | Strongest buy signal on the board — STRONG BUY-ADD cv100, BuyRank 1, on the bankable PullbackBuy_VWAP cell (+5). But the name is extended +6% above the pullback entry with an RSI divergence, so queue the pullback (no chase, FOMC-safe). Size is a deliberate token : LLY is already ~43% of sizing, so the single-name cap governs and trims the 0.5x val-mod add to a token. Fills only on a -5.7% pullback to 1165.58 (self-limiting). 12wk 1598 exceeds the DCF anchor. |
| SNOW | Snowflake Inc. | 262.74 | BUY — QUEUED @243.55 | 243.55 | 230.10 | 251.64 (+3.3%) | 270.50 (+11.1%) | 374.40 (+53.7%) | Fresh STRONG BUY on the bankable PullbackBuy_VWAP cell (+5), flipping up from ANTICIPATE over the session — the highest-quality clean buy on the board (news confirms: Q1 rev +33.5%, guide raised, fair-value reset to PTs -370, BofA Top Q3 idea). Extended +7.9% above entry, so queue the pullback (self-limiting, FOMC-safe). Repriced from the lapsed 07-07 @242.58 to the live model entry (provenance). on fill; 12wk 374 exceeds the DCF anchor. · news |
| AMD | Advanced Micro Devices, Inc | 516.11 | BUY | 517.00 | 475.88 | 550.46 (+6.5%) | 628.53 (+21.6%) | 735.46 (+42.3%) | Small event-staged starter: AMD sits AT its PullbackBuy entry (not extended), RSI 51, quality gate passes (F-Score 7) — the only Q-pass at-entry name in the pool. News confirms (Goldman PT to Wells Citi catalyst-watch; Advancing AI event 07-22/23). Sized down hard (0.5x val-mod x 0.75 FOMC-minutes caution = /) because adj conviction 66 only clears the floor by 1 and MoS is deeply negative. 12wk 735 exceeds the DCF anchor. · news |
| KLAC | KLA Corporation | 216.47 | HOLD | 216.47 | 207.00 | n/a | 267.05 (+23.4%) | 306.67 (+41.7%) | Marginal stop breach (-1.74%) on a recovery HOLD with a +42% 12wk view and +23% cost cushion; L2 combo (stop-break AND neg-12wk) not met and the 07-03 stop-break sell already stood down on recovery. Hold, reset stop to 207.00. |
| NBIS | Nebius Group, N.V. | 195.19 | HOLD | 195.19 | 191.00 | n/a | n/a | 239.86 (+22.9%) | Stop breach (-2.21%) but settled-close label is AVOID (intraday STRONG SELL-REDUCE faded, L4/L11); 12wk still +22.9% so L2 exit combo not met, and the overlay says keep the core / don't over-trim until the Meta-cloud question clears. Hold, reset stop 191.00; a stop-break WITH a negative 12wk would flip it to exit. |
Outcome & track record
Accuracy at the time of this record.
62 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 →
-0.132 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.
23 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.