Recommendations
0 to acquire · 1 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 |
|---|---|---|---|---|---|---|---|---|---|
| 2318 | Ping An Insurance | 53.90 | SELL 50% | 53.90 | 52.04 | 53.98 (+0.1%) | 53.38 (-1.0%) | 55.41 (+2.8%) | Ping An has printed a bearish signal for a third straight session (STRONG SELL - REDUCE cv65, Sell_Rank 1), with no news behind it. The written pre-commit for this case fires, so the book halves the remaining position; the 12-week estimate is only mildly positive (+2.8%). OPERATIONAL: 09-21 pre-commit 'third_bearish_print' (HF-P22 execute-on-trigger, HF-P55 next half tier) -> SELL market at the 09-23 open. The engine's 84.59% is not followed (HF-P64 over-trim record). PROFIT_ARMED is a near-cost artifact (Gain_ATR 1.13), suppressed per HF-P24. The remaining ride on stop RAISED 51.84 -> 52.04 (printed; ratchet-up), cushion 2.0 ATR. Next: a 4th bearish print cv>=65 -> SELL; a settled close < 52.04 -> SELL 500. Close-ref 53.90; reprice if the open gaps >1.5%. · news |
| 1299 | AIA Group | 76.25 | HOLD 1,400 | 76.25 | 75.75 | 76.29 (+0.1%) | 77.53 (+1.7%) | 81.73 (+7.2%) | AIA slipped to NO TRADE ('Consensus conflict + low conviction') but holds above its stop, and its 12-week estimate is still the best in the book (+7.2%), so it rides. OPERATIONAL: a single NO TRADE print (09-18 NT was followed by 09-21 HOLD 72, so this is not consecutive). PROFIT_ARMED is suppressed: underwater, Gain_ATR -0.24 (HF-P24). Stop HELD 75.75; cushion only 0.31 ATR. Pre-commits: settled close < 75.75 -> SELL 800; a 2nd consecutive NO TRADE on 09-23 -> SELL 400 (sustained NoTrade on a held name, CLAUDE.md §9). · news |
| 2888 | STANCHART | 239.40 | HOLD 600 | 239.40 | 236.73 | 237.85 (-0.6%) | 237.71 (-0.7%) | 232.80 (-2.8%) | StanChart fell 2.7% to 239.40 and conviction eased to 51, but it holds above its 236.73 stop, so there is no sell basis yet. OPERATIONAL: the arm is an artifact now (Gain_ATR 1.67 < 3; the inverted T12 232.80 < close drives T12_Progress 102.8%), so it is suppressed (HF-P50). Conviction -17 does not meet the -20 tick. Stop HELD 236.73 (printed 226.52); cushion 0.41 ATR. Pre-commit: settled close < 236.73 with Est_12W < close -> SELL 200. The 09-24 summit (-5/+3.5%) is hold-through. · news |
| 3968 | China Merchants Bank | 51.65 | HOLD 1,500 | 51.65 | 50.88 | 51.39 (-0.5%) | 51.28 (-0.7%) | 50.75 (-1.7%) | CMB is +6.2% on cost and still HOLD above its stop, so it rides. OPERATIONAL: Gain_ATR 2.82 < 3, and the T12-leg arm comes from an inverted T12 (50.75 < close), so it is suppressed (HF-P50). Stop HELD 50.88 (printed 49.17); cushion 0.72 ATR. Pre-commit: settled close < 50.88 with Est_12W < close -> SELL 500. · news |
| 3988 | Bank of China | 6.02 | HOLD 4,000 | 6.02 | 5.83 | 6.02 (+0.0%) | 5.95 (-1.2%) | 6.00 (-0.3%) | BOC is the book's best winner (+10.7%). It is armed for a profit-take, but no deterioration tick has fired, so the rule is to hold it on a raised trail rather than trim. OPERATIONAL: genuine arm (Gain_ATR 5.12). Ticks: (a) none; (b) conviction -12; (c) suppressed because the T12 is inverted (6.00 < close; HF-P50/51); (d) none. Trail HELD at 5.83 (the chandelier 2.0 ATR off the 6.06 high = 5.83; printed 5.68); cushion 1.68 ATR. · news |
| 0939 | CCB - H SHS | 9.74 | HOLD 2,000 | 9.74 | 9.46 | 9.75 (+0.1%) | 9.66 (-0.9%) | 9.70 (-0.5%) | CCB is flat on the day at +5.9% on cost and still HOLD, so it rides. OPERATIONAL: the arm is an artifact (Gain_ATR 2.79, inverted T12 9.70 < close), so it is suppressed. Stop HELD 9.46 (printed 9.35); cushion 1.46 ATR. Pre-commit: settled close < 9.46 -> SELL 1,000. · news |
| 3328 | Bank of Communications | 8.24 | HOLD 500 | 8.24 | 7.97 | 8.21 (-0.4%) | 8.24 (+0.0%) | 8.25 (+0.1%) | BoCom's remaining (an odd lot after yesterday's profit-take filled at 8.19) sit on a tight stop. The only fresh tick is the same dead-forward reading that was already banked, so there is no further trim. OPERATIONAL: armed (Gain_ATR 3.01). Tick (c) 8.25 < 1.02 x 8.24 re-fires, but it is the tick consumed by the 09-21 profit_take_2, and tick (c) is non-selecting on this book (HF-P51/66). Conviction (-15) is < 20. RSI_DIV has cleared. 30% of = 150 is sub-lot (HF-P65). Trail HELD 7.97 (printed 7.96); cushion 1.59 ATR. Pre-commit: settled close < 7.97 -> SELL 500. Re-arm counter 0. · news |
| 2388 | BOC Hong Kong Holdings | 52.30 | WATCH | 52.30 | 51.55 | 52.28 (-0.0%) | 52.23 (-0.1%) | 52.55 (+0.5%) | BOC HK dropped from BUY 68 back to WATCH 57, and it remains quality-gated (F-Score 4), so there is no entry. OPERATIONAL: re-evaluate only on a fresh BUY print that passes the quality gate; the 12wk estimate is flat (52.55). · news |
Outcome & track record
Accuracy at the time of this record.
52 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 →
6.000 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.
89 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.