Recommendations
0 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 |
|---|---|---|---|---|---|---|---|---|---|
| KO | Coca-Cola Co | 88.25 | SELL 30% | 88.25 | 87.69 | 88.43 (+0.2%) | 88.84 (+0.7%) | 90.02 (+2.0%) | Coca-Cola, the book's largest holding at and up about 5% on cost, flipped to a strong-sell on the book's most reliable exit pattern, so we bank 30% and keep the rest. We deliberately take the minimum tier: this is the first print, the stock is still above its 50- and 200-day averages, the 12-week view is still slightly positive (, +2.0%) and Wall Street's average target sits near - the signal says de-risk, not exit. OPS: late-flipped REDUCE (HOLD -> 65 -> SSR 68), engine portion 88.52% cut to 30% on single-print stability + positive 12wk (book precedent: CB first print 09-14 cut 30%). FailedBreakout_Down_20D|sell +1 (n=57, hit_1w.537) -> adj 69. MoS -2.13 (no tier bump). ADR-0012 armed (Gain_ATR 3.69, T12 98.0) but ticks NOT fired - tick (c) misses by (T12 vs 1.02x close); this is a signal exit, not a profit-take. Trail retained (model looser). RE-ARM: a 2nd consecutive SSR print or a close below -> SELL 50% of the balance. 12wk exceeds the DCF anchor. · news |
| MCO | Moody's Corp | 468.59 | SELL 50% | 468.59 | 450.30 | 463.42 (-1.1%) | 451.35 (-3.7%) | 416.88 (-11.0%) | Moody's has now printed a strong-sell two sessions running with conviction climbing from, and the chart is broken: is below both its 50-day and 200-day averages and the 12-week view is (-11%). Strong Q2 results have not stopped the slide, and the pattern has switched from the book's worst exit signal to its most reliable one, so we sell half now. OPS: stable REDUCE (SSR 63 -> SSR 78, Sell_Rank #3); signal family moved RallySell_BearTrend (-8) -> FailedBreakout_Down_20D (+1) -> adj 79, clears the floor without the >=75 haircut test. Engine 88.52% taken as 50% (book's second-cut cadence; MoS -0.99 no tier bump). The 09-17 rung did NOT fire; this is originated by the live signal. Stop stays (model lower; never lower a stop). Next rung: close below -> sell the balance. · news |
| SIRI | Sirius XM Holdings Inc | 27.31 | SELL 50% | 27.31 | 25.67 | 27.00 (-1.1%) | 26.29 (-3.7%) | 24.24 (-11.2%) | Sirius XM closed decisively through our protective stop (vs) with a 12-week view of (-11%) and the model now printing a sell, so we halve the position that is already 10% under cost. The early-September Deutsche Bank upgrade has been fully given back - the stock has slid from since - and we stop waiting for it. OPS: L2 stop-break + negative-12wk exit (close -0.79 ATR under the stop, beyond the -0.4 ATR graze band that held it on 09-17); the L2 basis bypasses the RallySell_BearTrend|sell -8 haircut (adj 47 would otherwise fail the floor). L3: act the first EOD it triggers. Quality_Pass False, FAIR_VALUE - no tier change. Stop re-based to the model's on the cut. Next rung: close below -> sell the balance. · news |
| LLYVK | Liberty Live Group Ser C | 96.28 | NO ACTION | 96.28 | 98.69⚠ | 94.81 (-1.5%) | 91.37 (-5.1%) | 81.55 (-15.3%) | Liberty Live's C shares closed below both our stop and the re-arm with a sharply negative 12-week view, which qualifies it for a half-sale, but three larger exits take tonight's slots. It is first in line next session. OPS: L2 FIRED (close vs stop, -0.90 ATR; 12wk, -15.3%; 7th NO TRADE). DISPLACED by the <=3 cap on dollar bleed ( vs SIRI). Valuation not priced (NA). If still below next EOD -> SELL 50% takes a slot ahead of any new sell. |
| NUE | Nucor Corp | 248.38 | NO ACTION | 248.38 | 253.64⚠ | 248.81 (+0.2%) | 249.81 (+0.6%) | 252.66 (+1.7%) | Nucor fell 6.3% and broke its trailing stop, and the model's conviction collapsed from with the 12-week view flattening to - a two-trigger profit-take on a winner still 12.5% above cost. At it is the smallest qualifying trade and is displaced by larger exits. OPS: ADR-0012 ARMED (T12_Progress 98.3, T12 > close) + FIRED on ticks (b) cv -25 and (c) T12 < 1.02x close -> profit_take_2 50% =. G1 n/a (not a fresh breakout, conv 60). Trail breach -0.54 ATR but 12wk positive so no L2. DISPLACED by the <=3 cap; takes a slot next EOD if the ticks still stand. |
| AAPL | Apple Inc | 336.13 | NO ACTION | 336.13 | 322.23 | n/a | n/a | 370.10 (+10.1%) | We trimmed 30% of Apple at Friday's open at and the remaining are held: the stock eased only 0.3% through the iPhone 18 Pro launch and triple witching, and the 12-week view is still The model went to no-trade, which we treat as a warning, not a second sale. OPS: ADR-0012 armed. Tick (b) NOT counted: conviction is a NO TRADE label (no score), and the same deterioration episode was already acted on 09-18. Tick (d) needs a 2nd consecutive NO TRADE -> SELL 30% next EOD. Trail retained. |
| AXP | American Express Co | 311.56 | WATCH | 311.56 | 301.25 | 315.60 (+1.3%) | 325.04 (+4.3%) | 254.43 (-18.3%) | American Express printed the book's only buy signal - a STRONG BUY on an oversold reversal - but we do not re-enter a name our quality screen fails, and the model's own 12-week view (, -18%) contradicts the bounce. OPS: Quality_Pass False blocks new entries (hard gate; AXP fully exited 09-12, = new entry). Single print after WATCH 62 x2. Report-only cell. RE-ARM: reconsider only if Quality_Pass flips True on the next fairvalue refresh AND the signal holds a 2nd print. |
Outcome & track record
Accuracy at the time of this record.
186 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 →
-0.078 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.
84 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.