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 |
|---|---|---|---|---|---|---|---|---|---|
| 2513 | Z.AI (Knowledge Atlas) | 614.50 | SELL 80% | 614.50 | 580.67 | 642.05 (+4.5%) | 719.51 (+17.1%) | 735.74 (+19.7%) | Z.AI printed a fifth straight lower close (614.50) under its 660.80 watch line on a live breakdown signal, and the sell-stop never filled, so the pre-committed escalation now sells at market. OPS: reconcile - 09-28 GTC SELL-STOP @594.81 EXPIRED unfilled 09-29 (low 603.00 > 594.81); HK-11 issue 3 = market-at-open (pre-committed 09-28: unfilled at expiry + close < 660.80 + bearish label); AVOID 46 BreakdownDown_20D (+2); valuation NA; residual stop 580.67 (engine sell-stop); model stop 723.75 > close refused (P6); estimator disagrees (+4.5% 1wk) and is down-weighted (T5). If unexecuted, RETIRE to WATCH 580.67 (HK-11 escalates once). · news |
| 0981 | SMIC | 61.05 | SELL 85.46% | 61.05 | 56.94 | 61.71 (+1.1%) | 61.89 (+1.4%) | 63.06 (+3.3%) | SMIC held a strong-sell on every print today (55-78, Sell_Rank #1) and settled a second session below its pre-committed 61.55 watch line; chip stocks were hit by the OpenAI pause news, and the valuation remains growth-priced-in. OPS: carry of the unexecuted 09-28 SELL (issue 2 of this cycle); T6 re-arm still fired (61.05 < 61.55); RallySell_BearTrend|sell +4 -> adj 59 (T6 is the basis, not the floor); 85.46% x (lot 500, R7); MoS -5.14 up-ranks, tier bump suppressed (G2/U7); residual 500 stop 56.94; hksemicon must not sell in parallel (L7). · news |
| 3750 | CATL | 482.20 | SELL 33% | 482.20 | 466.09 | 481.36 (-0.2%) | 489.81 (+1.6%) | 490.52 (+1.7%) | CATL settled a second session below its 486.40 watch line (482.20) with bearish prints all day, so a one-third trim steps out of the breakdown; it is deeply oversold and fairly valued, so the cut stays small. OPS: promoted from the 09-28 optional overflow into the free third slot; T6 re-arm fired on 2 settled closes; AVOID 59 FailedBreakout_Down_20D (+4) adj 63; the 476.76 stop is outside the live Entry_Price band (482.20 +/- 4.03), so it is repriced to market per provenance; RSI 22.0; residual stop 466.09 (close - 1 ATR; model 514.43 > close refused, P6). · news |
| 1347 | Hua Hong Semiconductor | 106.70 | HOLD | — | 105.00 | n/a | n/a | n/a | AVOID 63, close 106.70 +1.6% above WATCH 105.00; re-arm settled close < 105.00 OR settled REDUCE cv >= 65. |
| 0522 | ASMPT | 162.60 | HOLD | — | 155.96 | n/a | n/a | n/a | NO TRADE (Consensus conflict + low conviction); intraday low 155.50 pierced 155.96 but settled 162.60 (L4 settled close authoritative). |
| 0700 | TENCENT | 432.00 | HOLD | — | 420.11 | n/a | n/a | n/a | AVOID 42; close 432.00; model stop 454.91 > close refused (P6). |
| 0005 | HSBC | 159.00 | HOLD | — | 155.31 | n/a | n/a | n/a | NO TRADE cv0 on every settled print; close 159.00 +2.4% above WATCH; no PROFIT_ARMED origination (P1). |
| 0939 | CCB | 9.69 | HOLD | — | 9.45 | n/a | n/a | n/a | BUY - ADD 66 Buy_Rank #1 but PullbackBuy_VWAP|buy -9 -> adj 57 < 65; near-miss; stop 9.45. |
| 2888 | STANCHART | 242.80 | HOLD | — | 236.74 | n/a | n/a | n/a | HOLD 72; close 242.80; 12wk 236.65 negative so L2 re-arm on settled close < 236.74. |
| 7709 | XL2CSOPHYNIX | 40.00 | HOLD | — | 38.16 | n/a | n/a | n/a | HOLD 49; close 40.00; Micron 10-01 read-through priced 10-02. |
Outcome & track record
Accuracy at the time of this record.
246 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 →
-0.635 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.