Recommendations
2 to acquire · 3 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 |
|---|---|---|---|---|---|---|---|---|---|
| BAC | Bank of America Corp | 63.25 | ADD — QUEUED @61.52 | 61.52 | 59.57 | 62.20 (+1.1%) | 63.78 (+3.7%) | 75.21 (+22.3%) | Bank of America is the strongest technical setup in the book: a second consecutive STRONG BUY - ADD at conviction 90 on a VWAP-pullback signal, trading above every moving average with a trend score of 92 and a fresh 52-week-high close, backed by a Q2 beat with rising net interest income and a dividend that goes ex on 4 September. It is not cheap on a residual-income basis and carries a live AML compliance overhang, so we bid 2.7% under the market rather than chase the high. Provenance: the 08-04 GTC at went unfilled (session low 62.83), is WITHDRAWN, and is repriced to the live Entry_Price; expires 2026-08-10. Engine 99.33 (= / / 24% of book) CAPPED to the 30% tranche used for every prior BAC add. Quality gate N/A (ADD to a holding, Quality_Pass False blocks new entries only). Trail raised to the model stop NOT the 2.0xATR chandelier - the chandelier sits above the queued limit. L1 (favor PullbackBuy), L5 (f=0.30), L8 (executes at the next open). · news |
| DAL | Delta Air Lines Inc | 93.14 | ADD — QUEUED @87.30 | 87.30 | 84.07 | 89.24 (+2.2%) | 93.76 (+7.4%) | 110.76 (+26.9%) | Delta just posted 30% revenue growth and raised guidance, having answered the 2026 fuel shock by lifting fares and cutting low-return flying; analysts sit at a Moderate Buy with targets of -116 that bracket our own 12-week view, and the stock is up 24% this year against the market's 7%. The engine flipped it to STRONG BUY - ADD on a VWAP pullback, but the entry sits 6.3% under the market a whisker below a 52-week high, so we queue a limit and let the pullback come to us rather than buying strength. One-session emergence from HOLD cv63, so a limit and not a market order. Engine 99.33 (, doubles the line) CAPPED to a 30% tranche =; post-fill 0.91% of book. Quality_Pass True. Fill probability deliberately low; expires 2026-08-10. 12wk sits below the DCF anchor - no annotation. L1, L5 (f=0.30), L6 (no post-earnings gap-chase: Q2 is already 3+ weeks old), L8. · news |
| DVA | DaVita Inc | 188.69 | SELL 50% | — | 158.04 | n/a | n/a | 211.34 | DaVita fell 17% on results that were actually fine - adjusted EPS, revenue 55bn, treatment volumes ahead of plan and full-year guidance reaffirmed. What the market repriced is forward reimbursement: revenue per treatment slipped on a weaker commercial insurance mix, and CMS has proposed folding phosphate binders into the 2027 dialysis bundle at a rate update below the industry's cost trend. That is a structural de-rating rather than a bad quarter, so we halve the position to respect a risk line that was broken by 15% and keep the rest, because the rule is only proposed and the shares are deeply oversold. Exit basis: decisive stop-loss break (close 188.69 vs standing 222.80 = -15.31%) on 1.8x volume, closing near the 183.62 session low; anchor row NO TRADE cv0, Indeterminate consensus. Tier: 30% base bumped to 50% by MoS_FV -3.97 <= -3 (CLAUDE.md section 9b). G1/G2/G3 inapplicable - close is 17.4% below EMA20, this is loss prevention not a profit-trim. Stop RE-BASED 222.80 -> 158.04 (2.0xATR chandelier; the gap tripled ATR to 15.33). WATCH LINE: EMA200 - a decisive close below escalates the remaining to a full exit. 1wk/4wk n/a - Target_Price is blank on a NO TRADE row; engine band 132.08-205.26 tops out BELOW the 12wk 211.34. L2, L3 (execute promptly), L8. · news |
| NYT | New York Times Co Cl A | 65.48 | SELL 30% | 65.48 | 56.08 | 67.92 (+3.7%) | 73.60 (+12.4%) | 57.06 (-12.9%) | The New York Times beat on earnings with digital subscription revenue up 16% and digital advertising up 21%, but costs ran above guidance on variable pay and the shares fell 13% on the margin read-through, breaking our stop by 7% and dropping below the 200-day average with a negative 12-week outlook. We take the minimum trim: the operating business is compounding and the signal engine still reads this as an oversold reversal at RSI 33, so this is about honouring a broken risk line, not abandoning the story. Exit basis: L2 - decisive stop break (65.48 vs 70.40 = -6.99%) WITH a negative Target_12Week (57.06 = -12.86%), on 3.4x volume, 11.0% below EMA20 and 9.2% below EMA200. Held at the floor tier because the same row prints HOLD cv82 on ReversalUp_Oversold - the book's highest held conviction. Valuation: MoS -1.81 > -3, NO tier bump. Stop RE-BASED 70.40 -> 56.08 (model Stop_Price = 2.0xATR chandelier). Note the monotonicity contradiction: 4wk 73.60 (+12.4%) vs 12wk 57.06 (-12.9%) on one row. L2, L3, L8. · news |
| OXY | Occidental Petroleum Corp | 53.81 | SELL 50% | 53.81 | 50.23 | 54.88 (+2.0%) | 57.39 (+6.7%) | 51.86 (-3.6%) | Occidental has run 10% above our cost and the model's own 12-week view has now rolled over below the current price, with the shares slipping under both their 20- and 50-day averages. On an oil name priced well above its cash-flow anchor, that combination is the signal to bank half the gain and let the rest run on a wider stop. The three-session hold for the earnings date is over - Q2 was released after Wednesday's close. ADR-0012: armed (PROFIT_ARMED, Gain_ATR 2.74, T12_Progress 103.76%, +10.02%) + tick (c) dead forward view (12wk 51.86 < 1.02 x 53.81 = 54.89, -3.62%). One tick -> profit_take_1 30%, bumped to 50% by MoS_FV -3.17 <= -3 (section 9b). G1/G2/G3 inapplicable - not an uptrending name (below EMA20 54.94 and EMA50 54.81, RSI 46.2, -2.3% on the day). EXECUTION CAVEAT (L8): Q2 released post-close 08-05, call 08-06 1pm ET; consensus was adj EPS on 18bn rev, production 1,390-1,430 Mboe/d. If the 08-06 open gaps more than ~1.5%, REPRICE this card before executing. Stop RE-BASED 53.77 -> 50.23 (model) - the inherited trail sat 0.02xATR below spot, a guaranteed whipsaw. 12wk exceeds the DCF anchor. L3, L8. · news |
| GOOGL | Alphabet Inc Cl A | 362.43 | NO ACTION | — | 348.52 | n/a | n/a | 353.05 | Alphabet fell 4% on a genuinely worrying day: two senior AI researchers left for OpenAI and Anthropic, a California court refused Google and YouTube a new trial in the youth-addiction case, and investors remain uneasy about a $205bn AI spending plan. Our 12-week view has gone negative and momentum has collapsed, so a further trim is warranted - but with only three disposal slots today it loses out to a position banking more cash, and we hold the risk line tight instead. ADR-0012 armed (T12_Progress 102.66%) + tick (c) fired (12wk 353.05 < 1.02 x close). Tick (b) (conviction GATED as the structural NoTrade artifact ('Consensus conflict + low conviction', Conflicted consensus, price above EMA20/50/200) - 6th hand-gate of that signature. 30% = at +0.70%. Lost DISPOSE slot 3 to OXY on banked-dollar terms (vs) and section 9a MoS up-ranking (-3.17 vs -0.62). MANDATORY slot-1 candidate at the next EOD. Trail KEPT tight (armed-but-not-cut remedy). The 08-04 30% trims filled at ~382.94, +5.7% ahead of this close. Ledgered direction=none / optional=true so the counterfactual grader prices the non-execution. · news |
| GOOG | Alphabet Inc Cl C | 360.13 | NO ACTION | — | 347.25 | n/a | n/a | 352.22 | Alphabet fell 4% on a genuinely worrying day: two senior AI researchers left for OpenAI and Anthropic, a California court refused Google and YouTube a new trial in the youth-addiction case, and investors remain uneasy about a $205bn AI spending plan. Our 12-week view has gone negative and momentum has collapsed, so a further trim is warranted - but with only three disposal slots today it loses out to a position banking more cash, and we hold the risk line tight instead. ADR-0012 armed (T12_Progress 102.25%) + tick (c) fired (12wk 352.22 < 1.02 x close). Tick (b) (conviction GATED as the structural NoTrade artifact ('Consensus conflict + low conviction', Conflicted consensus, price above EMA20/50/200) - 6th hand-gate of that signature. 30% = at +1.11%. Lost DISPOSE slot 3 to OXY on banked-dollar terms (vs) and section 9a MoS up-ranking (-3.17 vs -0.62). MANDATORY slot-1 candidate at the next EOD. Trail KEPT tight (armed-but-not-cut remedy). The 08-04 30% trims filled at ~382.94, +5.7% ahead of this close. Ledgered direction=none / optional=true so the counterfactual grader prices the non-execution. · news |
| AAPL | Apple Inc | 311.00 | HOLD | 311.00 | 300.00 | n/a | n/a | 327.03 (+5.2%) | Largest position in the book at 15.4% and it just lost its 20-day average, flipping to AVOID at conviction 51. Armed on profit but no deterioration tick fires and the 12-week view is still positive, so we hold - but the event stop is now only 3.5% away and a decisive close below it exits all. Printed Stop_Price 332.07 is ABOVE the close (malformed AVOID-family row) - event stop KEPT. |
| AXP | American Express Co | 348.99 | HOLD | 348.99 | 334.75 | n/a | n/a | 357.74 (+2.5%) | Recovered from two sessions of NO TRADE to HOLD at conviction 61 with a flat 12-week view. Nothing actionable on a line; trail raised to the model stop. PROFIT_ARMED is spurious (Gain_ATR -0.42, position 0.84% underwater). |
| KO | Coca-Cola Co | 86.83 | HOLD | 86.83 | 83.64 | n/a | n/a | 95.93 (+10.5%) | Back to life at conviction 74 after three sessions of NO TRADE, with a 12-week view 10% above spot. Armed on profit but no tick fires - conviction rose rather than collapsed - so we hold and keep the trail. Tick (d) gated: the prior NO TRADE prints carry the structural 'Consensus conflict' reason. |
| CB | Chubb Ltd | 352.54 | HOLD | 352.54 | 341.96 | n/a | n/a | 370.96 (+5.2%) | Quiet HOLD at conviction 50, essentially flat against cost, 12-week view +5.2%. Chandelier sits below the standing trail so the trail is kept. PROFIT_ARMED spurious (Gain_ATR -0.11). |
| MCO | Moody's Corp | 483.98 | HOLD | 483.98 | 461.27 | n/a | n/a | 500.05 (+3.3%) | HOLD at conviction 57, marginally underwater, 12-week view +3.3%. No action; trail kept. PROFIT_ARMED spurious (Gain_ATR -0.40). |
| KHC | Kraft Heinz Co | 25.73 | HOLD | 25.73 | 25.25 | n/a | n/a | 29.30 (+13.9%) | The book's only genuinely cheap name - undervalued with a 12-week view 14% above spot and an adjusted conviction of 69 - but it prints HOLD, and HOLD is not a buy signal the engine will act on. Stranded for a third session. Stop re-based 25.70 -> 25.25 (the inherited trail sat 0.03xATR below spot, a guaranteed whipsaw). |
| SIRI | Sirius XM Holdings Inc | 30.70 | HOLD | 30.70 | 30.14 | n/a | n/a | 34.60 (+12.7%) | HOLD at conviction 59, flat against cost, 12-week view +12.7%. Trail raised to the model stop. |
| COF | Capital One Financial Corp | 221.63 | HOLD | 220.32 | 209.77 | n/a | n/a | 258.29 (+17.2%) | AVOID at conviction 49 on a mean-reversion-down signal after running 8% above cost at RSI 67. AVOID is not a REDUCE, so it does not enter the sell pool. Printed Stop_Price 227.43 sits above the close - malformed row; trail kept. |
| ALLY | Ally Financial Inc | 44.74 | HOLD | 44.74 | 42.63 | n/a | n/a | 42.99 (-3.9%) | AVOID at conviction 42 with a negative 12-week view, 1.2% underwater. Not a REDUCE; trail kept. Printed Stop_Price 46.88 is above the close - malformed row. PROFIT_ARMED spurious (-0.50). |
| VRSN | VeriSign Inc | 293.41 | HOLD | — | 276.38 | n/a | n/a | 326.41 | Conviction collapsed on an armed, 14% profitable position, which would mechanically fire a profit-take. Gated for the sixth time as the structural NoTrade artifact: the reason string is 'Consensus conflict + low conviction', the price is above every moving average, and the 12-week view is alive at +11.2%. Trail kept. |
| CVX | Chevron Corp | 186.41 | HOLD | 189.09 | 178.72 | n/a | n/a | 193.54 (+2.4%) | Broke its inherited trail by 1.6%, but that trail sat ABOVE the model's own stop - the over-tight ratchet pattern again. The row is a HOLD at conviction 62 on a VWAP pullback with a live 12-week view, so no exit; stop re-based to the model 178.72. Tick (d) gated (structural NoTrade pair). |
| NUE | Nucor Corp | 274.74 | HOLD | 274.60 | 255.59 | n/a | n/a | 344.49 (+25.5%) | HOLD at conviction 63 on a 20-day breakout, 24.5% above cost with a 12-week view 25% higher and yesterday's RSI divergence gone. The 30% trim executed at the 08-05 open. Trail raised. |
| LLYVA | Liberty Live Group Ser A | 99.94 | HOLD | 99.94 | 93.50 | n/a | n/a | 100.61 (+0.7%) | HOLD at conviction 73, faded from yesterday's 90 spike, still 4% underwater, no valuation coverage. Trail raised. PROFIT_ARMED spurious (-1.29). |
| LLYVK | Liberty Live Group Ser C | 103.71 | HOLD | 103.71 | 97.35 | n/a | n/a | 105.38 (+1.6%) | HOLD at conviction 73, faded from 85, 3% underwater, no valuation coverage. Trail raised. PROFIT_ARMED spurious (-1.02). |
| M | Macy's Inc | 25.51 | HOLD | — | 24.30 | n/a | n/a | 31.21 | Dropped from HOLD conviction 70 to NO TRADE and lost its profit-armed flag. Nothing actionable on a line; trail kept. |
| KR | Kroger Co | 56.68 | HOLD | 56.68 | 54.87 | n/a | n/a | 45.15 (-20.3%) | AVOID at conviction 56 with a 12-week view 20% below spot, 12% under its 200-day average. Below the floor on label; the 100% close-out is carried on its prior stop-break basis. /. |
| LEN | Lennar Corp Cl A | 87.88 | HOLD | 87.88 | 82.64 | n/a | n/a | 77.34 (-12.0%) | AVOID at conviction 62, 12-week view 12% below spot, 11% under its 200-day average. Close-out carried on the prior basis. / Trail raised. |
| LEN-B | Lennar Corp Cl B | 86.44 | HOLD | — | 81.78 | n/a | n/a | 77.12 | Flipped STRONG SELL - REDUCE to NO TRADE. 12-week view 11% below spot, 8.8% under the 200-day. Close-out carried on the prior L2 basis. / Trail raised. |
| STZ | Constellation Brands Cl A | 130.64 | HOLD | 130.64 | 125.53 | n/a | n/a | 102.73 (-21.4%) | Third stop breach (-4.1%) and slipped from STRONG SELL - REDUCE to AVOID at conviction 56, with a 12-week view 21% below spot. Standing 100% close-out carried; stop re-based. /. |
| NVR | NVR Inc | 6365.78 | HOLD | 6365.78 | 5954.11 | n/a | n/a | 5748.17 (-9.7%) | The only stable label-based REDUCE left in the book - STRONG SELL - REDUCE at conviction 75, the top sell rank, for a third consecutive session, with a 12-week view 10% below spot. Standing 100% close-out carried; / too small to consume a disposal slot. Trail raised. |
| — | Jefferies Financial Group | — | NO ACTION | — | — | n/a | n/a | n/a | Clears the conviction floor at an adjusted 67 on a second consecutive BUY print, but it is a NEW entry in a company that fails the quality screen (F-Score 5, quality rank 18.), so the gate blocks it for a fourth session. Becomes live the moment its F-Score improves on a valuation refresh. Conviction also slipped. |
Outcome & track record
Accuracy at the time of this record.
71 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 →
0.025 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.
46 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.