Recommendations
1 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0992 | LENOVO GROUP | 33.80 | BUY — QUEUED @33.58 | 33.58 | 28.62 | 33.66 (+0.2%) | 34.80 (+3.6%) | 34.54 (+2.9%) | Lenovo broke to a new 52-week high on heavy volume and the model upgraded it to STRONG BUY at conviction 85; valuation is roughly fair and the quality screen passes, so we queue a limit at the model entry rather than chasing the +8% day. Sizing 71.55% x 600k x 20% = 85,860 -> (lot); engine buy-stop @33.58 is already through the 33.80 close, so queued as a GTC limit at the same price; re-arm from 09-14 (BUY-family cv>=65) met; L7: hksemicon/hktech already hold 0992 - no sub-book double-; Target_Price 43.50 is the risk objective. · news |
| 0005 | HSBC HOLDINGS | 160.90 | SELL 50% | 160.90 | 155.31 | 161.00 (+0.1%) | 160.39 (-0.3%) | 160.96 (+0.0%) | HSBC is still closing below the stop it broke decisively on 09-15, the model's forward view is flat, and it is the book's largest position, so we carry the half-position trim. Carried card session 2 (unexecuted 09-16); below floor (adj 52) - carried by the recorded-stop break (163.18, close 160.90, 0.82 ATR); retire on a settled close >= 163.18; residual stop 155.31, pre-execution line 163.18. · news |
| 1347 | HUA HONG SEMICONDUCTOR | 111.90 | SELL 85.46% | 111.90 | 98.41 | 113.89 (+1.8%) | 119.56 (+6.8%) | 119.04 (+6.4%) | Hua Hong's bounce failed under its breakout line and the model flipped to a high-conviction STRONG SELL - REDUCE (76, up from 27); the position is 30% under cost and valuation is stretched, so we cut two-thirds. 85.46% -> (lot 1,000, R7 downward); G2 suppresses the valuation amplify (DCF blank); estimator disagrees (T5/P2); fresh REDUCE at cv>=65 re-opens the HK-11-retired WATCH 105; residual stop 98.41. · news |
| 3750 | CATL | 501.00 | SELL 85.46% | 501.00 | 452.51 | 507.06 (+1.2%) | 514.62 (+2.7%) | 511.93 (+2.2%) | CATL closed below its stop while the breakdown signal strengthened for a fourth session to STRONG SELL conviction 83, the top-ranked sell in the book, so we cut two-thirds of the position. Stop 511.94 breached (-2.14%, 0.49 ATR); action 501.00 inside the Sell Limit 504.74 +/-0.25 ATR band; market-at-open (HK-11 escalation already spent, signal not decayed -> carried); RSI 20.7 - 1-week instrument (HK-9); residual stop 452.51. · news |
| 0981 | SMIC | 63.65 | NO ACTION | 63.65 | 62.78 | 63.65 (+0.0%) | 64.70 (+1.6%) | 68.75 (+8.0%) | SMIC still prints a high-conviction STRONG SELL - REDUCE but reclaimed its pre-committed 62.78 line on a +4.8% day, so it ranks fourth behind the stop-break and fresh-signal sells. Cap overflow #4 (bleed 136.0k vs 3750 128.4k; 3750 wins on monitor breach + adj 85); HK-11 session 3, signal not decayed -> carried; a settled close < 62.78 promotes it. · news |
| 0700 | TENCENT | 433.40 | HOLD | 433.40 | 416.17 | n/a | n/a | 423.97 (-2.2%) | Tencent's repeated REDUCE signal has faded to AVOID, so the unexecuted sell is retired to a price watch. HK-11 retirement on signal decay; re-arm: settled close < 416.17 OR REDUCE cv>=65; model stop 453.98 above close refused (P6). · news |
| 0823 | LINK REIT | 37.06 | HOLD | 37.06 | 36.74 | n/a | n/a | 36.19 (-2.3%) | Link REIT's SELL - REDUCE has faded to AVOID, so the carried sell is retired to a watch on the 36.74 stop, which sits under 1% below the close. HK-11 retirement on signal decay; re-arm: settled close < 36.74 OR REDUCE cv>=65; model stop 38.32 above close refused. · news |
| 2513 | Z.AI (KNOWLEDGE ATLAS) | 720.00 | HOLD | 720.00 | 660.80 | n/a | n/a | 806.87 (+12.1%) | Rebound to 720 with an oversold-reversal HOLD at conviction 90; hold on the 660.80 watch line. HK-9(c) not a re-entry case; model stop 490.66 degenerate refused. · news |
| 2888 | STANDARD CHARTERED | 244.00 | HOLD | 244.00 | 236.74 | n/a | n/a | 236.73 (-3.0%) | HOLD cv70; stop 236.74 kept (model 232.39 lower). · news |
| 0939 | CCB | 9.64 | HOLD | 9.63 | 9.45 | n/a | n/a | 9.61 (-0.3%) | HOLD cv64; stop 9.45 kept (model 9.21 lower); conviction flip-flop 0/100/0/64. · news |
| 7709 | XL2CSOPHYNIX | 39.12 | HOLD | 39.12 | 34.40 | n/a | n/a | 40.21 (+2.8%) | AVOID cv47 on a 2x ETF - leveraged rule needs cv>=70 + 3 prints + stop break; hold on 34.40 (model 47.28 above close refused). · news |
Outcome & track record
Accuracy at the time of this record.
224 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 →
-0.220 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.
88 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.