Recommendations
2 to acquire · 14 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 |
|---|---|---|---|---|---|---|---|---|---|
| LLYVA | Liberty Live Group Ser A | 102.71 | ADD | 102.50 | 97.19 | 107.45 (+4.8%) | 119.01 (+16.1%) | 106.18 (+3.6%) | Liberty Live's Series A tracker broke out to a 52-week high on the 12-Aug close and the model now rates it the book's single best buy, so we are adding roughly 30% to the existing stake at the breakout level. The Live Nation stake behind the tracker keeps compounding while the tracker itself still trades at a wide discount to it, and the position is small enough that a full-size add barely moves the book. There is no fresh news either way -- August 6 earnings are already digested. OPS: adj conviction 68 (val NA, no scorecard cell) clears the 65 floor; Buy_Rank 1; Entry_Distance_ATR -0.08 so no chase. L1 caveat: BreakoutUp_52W 4wk targets historically overshoot and mean-revert -- note the model's own 4wk (+16.1%) sits ABOVE its 12wk (+3.6%). Exit_Warning prints RSI_DIV+PROFIT_ARMED but the ADR-0012 profit-take is SUPPRESSED because the engine's own Action on the row is a bullish ADD. Stop raised -> (model-printed). Same underlying as the LLYVK card -- combined into one economic exposure. |
| LLYVK | Liberty Live Group Ser C | 106.49 | ADD | 105.92 | 100.86 | 110.64 (+4.5%) | 121.65 (+14.9%) | 111.00 (+4.8%) | The Series C line of the same Liberty Live tracker printed the identical 52-week breakout and the same buy rating, so we add about 30% here too. It is the larger of the two classes we hold and carries the better forward view of the pair, and the stake is still marginally below cost, so this is an add into strength rather than a chase of a winner. OPS: adj conviction 68 (val NA), Buy_Rank 2; Entry_Distance_ATR -0.23, just inside the -0.25 no-chase line -- executed at the printed Entry_Price, not the close. Same L1 overshoot caveat and same BUY-ADD suppression of the RSI_DIV/PROFIT_ARMED profit-take as LLYVA. Stop raised ->. Deliberately taking both slots on one underlying; flagged, not vetoed (CLAUDE.md 9). |
| BAC | Bank of America Corp | 64.81 | SELL 30% | 64.81 | 62.54 | 65.94 (+1.7%) | 68.59 (+5.8%) | 77.76 (+20.0%) | Bank of America has run up nearly 8% for us and is now the most overbought name in the book at an RSI of 74, and the model's confidence in it has halved in a single session even as the price kept climbing -- price up, conviction down is the classic distribution pattern. We are banking a third of the gain and letting the other two-thirds run; the twelve-week view is still strongly positive, so this is profit discipline, not a change of mind on the bank. The 12-Aug announcement of a $250bn infrastructure-lending initiative is a genuine positive but it is a plan, not an earnings surprise, and it does not change the case for taking something off after a 5 ATR move. OPS: ADR-0012 profit-take, PROFIT_ARMED (Gain_ATR 4.94) + tick (b) conviction (-25 pts). 1 tick -> profit_take_1 = 30%. G1 does not protect (conviction 45, well under 80) and tick (b) fires regardless of G1. Valuation OVERVALUED_VS_RI MoS -0.46 -> val_adj -2, no tier bump. Action price is the close, 0.40 ATR above the printed Entry_Price -- that entry is a BUY level on a HOLD row, not a sell reference. Give-up stated plainly: the trimmed slice forgoes a modeled +20% at 12 weeks. Stop raised ->. Ex-div on 09-04 unaffected. · news |
| AAPL | Apple Inc | 302.25 | SELL 50% | 302.25 | 300.00 | 300.23 (-0.7%) | n/a | 295.52 (-2.2%) | Apple has fallen about 10% since its 30-July earnings and the model has refused to give it a tradable signal for five straight sessions while its twelve-week outlook has slipped below the current price. Management's own flag of a '100-year flood' in memory pricing is a real margin drag, Jefferies moved to underperform with a target on 10-Aug, and the position is now underwater for us. We halve what is left rather than wait for a signal the engine is not producing. The counterweight is honest: the 46-analyst consensus target of still sits about 7% above the price and Wedbush is at so this is a de-risk into an unresolved argument, not a verdict that Apple is broken. OPS: ADR-0012 armed (T12_Progress 102.3) + tick (c) dead 12wk (, -2.2%) + tick (d) 5 consecutive NO TRADE -> 2 ticks -> profit_take_2 = 50%. HONEST CAVEAT: Unreal -2.07%, Gain_ATR -0.83 -- this is a LOSING position wearing a PROFIT_ARMED flag; the arm comes purely from the T12_Progress clause (Systemic finding 1, third night). Valuation MoS -2.83 -> val_adj -10 but no tier bump (-2.83 > -3). Scorecard NoTrade|sell flipped to +1 this run (n=19, hit_1w.538). No Target_Price on a NO TRADE row -> 4wk n/a, 1wk interpolated off the 12wk at f=0.30 (L5, calib_1w 0.006 degenerate). 12wk exceeds the DCF anchor -- projection assumes growth beyond priced-in. Cumulative cut reaches 82.5% of the 49,865-sh seed lot. Stop held on the residual. · news |
| MCO | Moody's Corp | 477.84 | SELL 50% | 477.84 | 461.27 | 477.11 (-0.2%) | n/a | 475.42 (-0.5%) | Moody's has gone four sessions without a tradable signal, its twelve-week outlook has now dipped below the current price, and the company itself cut 2026 operating-margin guidance while leaning harder on buybacks -- a company its share price rather than growing into it. On top of that, investors are actively re-rating Moody's exposure to deteriorating private-credit recoveries, and the most-followed fair-value narrative now sits below the market price. We take the second half of the position off and keep a third of the original stake. OPS: ADR-0012 armed (T12_Progress 100.5) + tick (c) dead 12wk (, -0.5%) + tick (d) 4x NO TRADE -> 2 ticks -> profit_take_2 = 50%. This card was ledgered optional:true on 08-11 and deferred once -- L3 says stop re-deferring, so it executes tonight. Same PROFIT_ARMED-on-a-loss caveat as AAPL (Unreal -2.20%). Valuation MoS -1.00 -> val_adj -5, no tier bump. Ex-div on 08-14: selling at the 08-13 open forgoes on the sold slice -- immaterial, stated. Stop held on the residual. · news |
| AXP | American Express Co | 344.08 | SELL 50% | 344.08 | 334.75 | n/a | n/a | 344.57 (+0.1%) | Fires again at the 50% tier (armed T12_Progress 99.9 + tick (c) 12wk vs 1.02x close + tick (d) 2x NO TRADE) and is #1 by dollar bleed at -- and is DEMOTED for the second night on an unchanged news override: the 07-24 Q2 beat (revenue +10% to 64bn, EPS vs) with FY26 revenue growth guidance RAISED to 10%, a Moderate Buy consensus across 31 analysts, and an excess-returns intrinsic value above the price. The discriminator vs the cards that DID execute: AXP's 12wk is +0.14% -- flat, not negative -- so it fails tick (c) only on the 1.02x margin, and the position moved UP +0.96% while deferred last night. ESCALATION COMMITMENT so this does not drift a third time: executes UNCONDITIONALLY at the next EOD if the 12wk turns negative OR the close breaks the stop, news notwithstanding. · news |
| CB | Chubb Ltd | 343.33 | SELL 30% | 343.33 | 341.96 | n/a | n/a | 346.70 (+1.0%) | Newly fired (armed T12_Progress 99.0 + tick (c)) and #2 by dollar bleed at, but demoted below MCO for the third slot on three grounds: the 12wk is, +0.98% ABOVE the close, failing 1.02x by three pennies of margin; it has exactly ONE NO TRADE print, and last night's own interpretive note says a single flip to NO TRADE is not a tick-(b) conviction collapse; and conviction was 50 as recently as last session. Stop held -- only 0.4% under the close, so the line is already tight. Mandatory candidate next EOD. |
| GOOGL | Alphabet Inc Cl A | 343.54 | SELL 30% | 343.54 | 319.70 | n/a | n/a | 315.34 (-8.2%) | Re-fires 30% (armed + tick (c), 12wk = -8.2%) after the 08-11 30% cut filled at. Label degraded HOLD cv52 -> AVOID cv50 on FailedBreakout_Down_20D. The overlay's standing 'invalidated when close below 345' override stays invalidated (close). Deferred on slot arithmetic only. Note the printed Stop_Price is a SHORT-side level on an AVOID row -- ignored; the long stop stays. · news |
| KHC | Kraft Heinz Co | 24.53 | SELL 30% | 24.53 | 24.15 | n/a | n/a | 24.69 (+0.7%) | Newly fired 30% (armed + tick (c), 12wk vs 1.02x close -- dead by 1.3%). Signal is RallySell_BearTrend, which is this book's WORST actionable cell at bias -8 (n=8, hit_1w.125), so a signal-originated sell here would need raw conviction >= 75 and KHC prints 52 -- only the ADR-0012 profit-take survives, and it is the marginal tier. Position -3.31%; at 30%. |
| DVA | DaVita Inc | 181.50 | SELL 50% | 181.50 | 174.64 | n/a | n/a | 130.69 (-28.0%) | Re-fires at 50% (armed + tick (c) 12wk = -28.0% + tick (d) 6x NO TRADE). Worst holding in the book at -22.7%. Still held on the same argument as last night: RSI 25.9 is a washout print and the name actually rose from to this session. Deferred a second time -- the counterfactual says that costs a median +2.81% at 4wk. Stop held. |
| SIRI | Sirius XM Holdings Inc | 28.44 | SELL 30% | 28.44 | 28.60⚠ | n/a | n/a | 27.97 (-1.7%) | Re-fires 30% (armed + tick (c), 12wk = -1.7%) AND is a live stop breach -- vs the recorded, the second consecutive close below. The 08-11 STRONG SELL - REDUCE cv60 collapsed to NO TRADE cv0, which removes the signal-originated route (and that RallySell cell is -8 anyway). Stop deliberately HELD at despite the breach: loosening a breached stop while declining to cut size is precisely the failure ADR-0020 exists to catch, so the monitor keeps flagging it until this trim executes. |
| COF | Capital One Financial Corp | 222.44 | SELL 50% | 222.44 | 214.90 | n/a | n/a | 260.47 (+17.1%) | Newly fired at the 50% tier -- armed (Gain_ATR 3.94, +8.4%) + tick (a) RSI_DIV + tick (b) conviction (-29). Two ticks. G1 offers no protection at conviction 25. Best-in-book forward view survives though: 12wk (+17.1%). Trail raised -> while the trim waits. at 50%. |
| ALLY | Ally Financial Inc | 44.25 | SELL 50% | 44.25 | 42.63 | n/a | n/a | 41.80 (-5.5%) | The only genuine signal-originated sell in the book tonight: STRONG SELL - REDUCE, Portion 88.5%, conviction 75, Sell_Rank 1, on FailedBreakout_Down_20D (actionable cell, bias -1, n=35) -- adj 74. 12wk = -5.5%. Tier SCALED DOWN one step from 88.5% to 50% because valuation reads UNDERVALUED (MoS +0.05, the only positive MoS among held names): selling cheap, so trim the minimum. Deferred purely on size -- does not outrank a card. Stop held (tighter than the model's). |
| GOOG | Alphabet Inc Cl C | 342.37 | SELL 30% | 342.37 | 320.20 | n/a | n/a | 315.77 (-7.8%) | Same underlying, same case as the GOOGL Cl A line (armed + 12wk -7.8%, AVOID cv50). /. Execute alongside the Cl A trim whenever that slot. · news |
| NYT | New York Times Co Cl A | 63.95 | SELL 49% | 63.95 | 59.62 | n/a | n/a | 42.66 (-33.3%) | A live SELL - REDUCE (Portion 49%, conviction 55, BreakdownDown_20D) with the most negative forward view in the book: 12wk = -33.3%. Already halved twice (08-07 and 08-12 fills). Deferred on size --. RSI 33.4 continues to argue against selling the low a fifth time. Stop raised ->. |
| NUE | Nucor Corp | 271.81 | SELL 30% | 271.81 | 259.19 | n/a | n/a | 344.78 (+26.8%) | Fires on tick (d) alone (4x NO TRADE) with the 12wk strongly ALIVE at (+26.9%). Best holding in the book at +23.1% / Gain_ATR 7.29. Trailing still beats trimming here; ledgered for completeness at. Stop held. |
| KO | Coca-Cola Co | 86.71 | HOLD | 86.71 | 83.81 | n/a | n/a | 94.08 (+8.5%) | Armed (T12_Progress 92.2, +3.05%) with ZERO ticks -- conviction is only -11, and the 12wk (+8.5%) is comfortably alive. Last night's acquire near-miss reverted from BUY - ADD to HOLD, so it is not a buy candidate tonight either. Mandatory trail-raise per ADR-0012: stop held (the model prints the same level). /, the book's 3rd-largest line. |
| DAL | Delta Air Lines Inc | 89.93 | HOLD | 89.93 | 88.93 | n/a | n/a | 103.02 (+14.6%) | Reverted HOLD cv61 -> NO TRADE, but the 12wk is the 2nd-best in the book at (+14.6%) and the name is not armed. Stop held, 1.1% under the close. /. |
| M | Macy's Inc | 23.79 | HOLD | 23.79 | 23.35 | n/a | n/a | 26.55 (+11.6%) | DEVIATION FROM LAST NIGHT, STATED. On 08-11 this entry said 'a second close below is an exit'; that second close has now happened (then, -3.2% through the line). The exit does NOT fire because L2 requires stop-break AND a negative 12wk -- here the 12wk is, +11.6% POSITIVE, the engine has re-armed a bullish FailedBreakdown_Up_20D HOLD cv49, and it printed a fresh lower stop. Stop RE-BASED -> (model-printed). /. If breaks, that is the exit, no further conditions. |
| KR | Kroger Co | 56.06 | HOLD | 56.06 | 54.87 | n/a | n/a | 43.69 (-22.1%) | 5th consecutive AVOID with a 12wk of (-22.1%), armed and fired on tick (c) -- but valuation reads UNDERVALUED (MoS +0.06) so the tier scales down to the minimum, and 30% of is /. Not economically actionable. Stop held. |
| NVR | NVR Inc | 6293.95 | HOLD | 6293.95 | 6069.66 | n/a | n/a | 5780.83 (-8.2%) | Armed with a dead 12wk (, -8.2%). -- a 30% trim is one share. Not actionable. Stop held. |
| STZ | Constellation Brands Cl A | 133.96 | HOLD | 133.96 | 128.06 | n/a | n/a | 114.02 (-14.9%) | Armed with a dead 12wk (, -14.9%); /. Stop held. |
| LEN | Lennar Corp Cl A | 85.20 | HOLD | 85.20 | 82.64 | n/a | n/a | 76.59 (-10.1%) | Armed with a dead 12wk (, -10.1%); /. Model's stop is looser -- stop held. |
| LEN-B | Lennar Corp Cl B | 83.42 | HOLD | 83.42 | 81.78 | n/a | n/a | 75.85 (-9.1%) | Same case as the Cl A line at / Stop held. |
| JEF | Jefferies Financial Group | 54.82 | WATCH | 54.82 | — | n/a | n/a | 55.13 (+0.6%) | never seeded. Decayed BUY cv74 -> BUY cv67 -> NO TRADE -> WATCH cv49 -> WATCH cv42 over five sessions. No position to defend, no actionable entry. |
| LPX | Louisiana-Pacific Corp | 73.66 | WATCH | 73.66 | — | n/a | n/a | 70.50 (-4.3%) | never seeded. WATCH cv52 on FailedBreakdown_Up_20D with a negative 12wk (, -4.3%) and the worst valuation in the file (MoS -5.25). Not a candidate. |
Outcome & track record
Accuracy at the time of this record.
85 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 →
0.006 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.