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 |
|---|---|---|---|---|---|---|---|---|---|
| 2888 | Standard Chartered | 220.80 | HOLD | 220.80 | 214.98 | 221.97 (+0.5%) | 224.38 (+1.6%) | 222.80 (+0.9%) | We are holding Standard Chartered through a third down session. The position is 3.4% below our entry, but nothing that would justify selling has actually happened: there is no sell signal, conviction is unchanged, the shares remain far above their long-term trend line, and the price is still above our protective stop. The bank's fundamentals are constructive - a record first quarter with income up 9% and its wealth business up 32% - and half-year results due around 29 July are the realistic catalyst for a re-rating either way. We hold to that print on the existing stop rather than cutting into a drawdown. OPERATIONAL: HOLD FailedBreakdown_Up_20D cv50 (4th flat print), close 220.80, RSI 56.4, EMA200 184.52. Exit_Warning=PROFIT_ARMED fires AGAIN on a LOSS (Gain_ATR -1.44, T12_Progress 99.10) - SUPPRESSED as a cost-inverted T12 artifact (HF-2 widened): Target_12Week 222.80 < Avg_Cost 228.63, so 99% of target never repays the entry; fire-tick (c) (222.80 < 1.02 x 220.80 = 225.22) is the same inversion double-counted and is suppressed with it. No legitimate exit leg: no SELL label, no other Exit_Warning (tick a), conviction flat (tick b), not 2x NO TRADE (tick d), no stop break, 12wk non-inverted vs close (+0.91%); L2 fires on neither leg; overlay override endorses the hold; HF-6 3rd session. STOP 214.98 UNCHANGED (scan chandelier widened to 209.96 - we keep the tighter recorded level); NO trail-raise (no profit to protect). Cushion 5.82 = 1.07 ATR, compressing 1...07 across three sessions. Remaining risk HK. CATALYST: H1 results ~2026-07-29 = 6 sessions out; enters the <=5-session catalyst-aware-hold window at tomorrow's EOD (hold/trail through the print, no pre-trim). · news |
| 0966 | China Taiping Insurance | 21.36 | NO ACTION | 21.38 | 18.68 | 21.25 (-0.6%) | 20.68 (-3.3%) | 20.57 (-3.8%) | China Taiping was the only genuine buy candidate in the book today and the strongest conviction reading we have seen in weeks, helped by being the one name here that screens as cheap on intrinsic value. We passed anyway. It fails our fundamental quality screen, which blocks it outright as a new position. More telling, the model's own forecasts contradict its own buy signal: it projects the shares 3.7% LOWER in twelve weeks, and below our entry price within a week. That combination - a loud buy signal with a quiet downward forecast - is precisely the pattern that produced the losing position we are already carrying. A cheap stock the model expects to fall is not a bargain yet. OPERATIONAL: STRONG BUY BreakoutUp_20D cv83, Buy_Rank 1, close 21.36 (+3.3%), entry 21.38 (+0.02 ATR, non-extended), stop 18.68, target 26.80, RSI 60.8, ATR 1.05. adj_conv 88 = 83 + val_adj +5 (UNDERVALUED MoS +0.791 -> clamp(round(15.8),0,10)=+10, HALVED to +5 because Quality_Pass=False) + bias 0 -> clears the 65 floor easily. BLOCKED by: (1) HARD quality gate Quality_Pass=False on a NEW entry (F-Score/FCF); (2) HF-3 inverted 12wk Est_12W 20.57 < Close 21.36 (-3.7%); (3) HF-4 Est_1W 21.25 < entry 21.38. Compounding: BreakoutUp_20D|buy 0/3 on this book historically (L1); ex-div HKon 2026-07-08 shapes the setup; printed AVOID FailedBreakout_Down_20D for the 3 prior sessions (cv 58/33/62) - a one-day AVOID->STRONG BUY flip is not a stable signal. NOT QUEUED - a limit under a -3.7% 12-week path is a zombie order by construction. RE-ARM: Quality_Pass=True AND Est_12W > Close AND Est_1W >= entry at cv>=65; or a pullback toward EMA200 19.80 that re-prints the breakout from a base. |
| 0005 | HSBC Holdings | 156.50 | NO ACTION | — | — | 154.76 | 158.20 | 160.46 | Yesterday we declined to queue an anticipation buy in HSBC because the model's one-week forecast sat below the trigger price we would have paid. Today the shares fell and the signal vanished entirely - the trigger was never reached, so the order would not have filled. The stand-down cost nothing and the caution was correct. We stay out until the setup rebuilds with forecasts that at least agree with the entry price. OPERATIONAL: NO TRADE cv0 ('Consensus conflict + low conviction'), close 156.50 (-1.30), RSI 66.54 (cooling from 71.95). Yesterday's BUY-ANTICIPATE cv79 buy-stop 158.67 was NEVER TOUCHED -> the withheld queue would not have filled; HF-4's first clean counterfactual win. ANTICIPATE streak now 1/3 over the last three prints (07-17 no, 07-20 yes, 07-21 no) -> below the >=2/3 structural gate for the anticipate slot. Est_1W 154.76 still below yesterday's entry. RE-ARM (unchanged): >=2/3 ANTICIPATE prints at cv>=55 WITH Est_1W >= entry AND a non-inverted 12wk -> anticipate slot at 0.5x size; OR a non-extended actionable BUY at cv>=65 meeting the same two estimation legs -> acquire slot. Note H1 results ~2026-07-30 (+-5% band) - any fresh entry inside that window needs catalyst-aware framing. |
| 2388 | BOC Hong Kong Holdings | 47.06 | NO ACTION | 47.06 | 46.54 | 46.88 (-0.4%) | 46.83 (-0.5%) | 46.95 (-0.2%) | BOC Hong Kong was yesterday's top-ranked buy candidate, which we rejected on quality and on a twelve-week forecast pointing lower. One session later the signal has decayed by more than twenty points and the shares are flat - it went nowhere, exactly as the forecast implied. Nothing improved on the fundamental screen. It stays off the list. OPERATIONAL: WATCH FailedBreakdown_Up_20D cv46 (from cv68 BUY Buy_Rank 1 on 07-20, -22 pts), close 47.06 (-0.04), RSI 58.0. adj 45 after val_adj -1 (OVERVALUED_VS_RI MoS -0.174) -> well below the 65 floor. Quality_Pass still False; Est_12W 46.95 still below close (-0.23%); Est_1W 46.88 < entry. L1 weakest buy family. RE-ARM: quality-pass turn (Q=True) AND non-inverted 12wk AND Est_1W >= entry, at cv>=65. |
Outcome & track record
Accuracy at the time of this record.
3 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 →
0.184 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.
22 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.