This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.

HK End-of-Day Verdict 18 Sept 2026, 16:00:00 GMT+8

Hong Kong — End-of-Day Verdict

EOD 2026-09-18 (hk)

Recommendations

1 to acquire · 3 to dispose

TickerNameCloseActionAction 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
0939China Construction Bank (H)9.59ADD — QUEUED @9.559.559.159.59 (+0.4%)9.58 (+0.3%)9.51 (-0.4%)CCB printed a fresh pullback-to-VWAP add signal at the close (Buy_Rank #1), the book's most reliable buy pattern, trading above its 20- and-day averages; valuation is blind for this listing, so we queue the add at the model entry just below the close rather than paying up. OPS: single closing print after HOLD 60-61 intraday; 12wk flat (9.51) - the weak leg; 63.97% x = (lot); stop 9.15 (2.0 ATR) for the combined position after fill, 9.45 until then; L7 hkfin holds 0939 - execute once from hk. · news
2513Z.AI (Knowledge Atlas)780.00SELL 85.46%780.00660.80820.95 (+5.3%)869.85 (+11.5%)865.25 (+10.9%)Z.AI held a strong sell-and-reduce signal on every print for two sessions, with the intraday rally to 795 failing far below its 20-day average while the placement and convertible-bond overhang still weighs; the largest dollar risk in the book, so cut most of it. OPS: session 2 of the 09-17 card (HK-11 limit not reached); 85.46% x (R7 downward); residual on WATCH 660.80; estimator points up (+5-11%) - P2 high-ATR pattern, T5 down-weight; -52.29% vs Avg_Cost 1,635. · news
1347Hua Hong Semiconductor115.50SELL 85.46%115.50105.00117.42 (+1.7%)121.94 (+5.6%)124.68 (+7.9%)Hua Hong flipped back to a stable strong sell-and-reduce signal on all six prints, meeting the re-arm trigger we pre-committed when the last sell was retired; it is also the most richly priced name in the book versus fair value, which moves it up the sell list. OPS: T6 re-arm 'REDUCE cv>=65' fired (cv76); MoS -18.05 up-rank only (no tier at 85.46%); x 85.46% = (lot); residual stop 105.00; 12wk estimate exceeds DCF anchor; -27.81% vs cost 160. · news
0981SMIC65.15SELL 85.46%65.1561.5565.15 (+0.0%)66.11 (+1.5%)71.19 (+9.3%)SMIC printed a stable strong sell-and-reduce signal all session, under its VWAP and-day average, firing the promotion trigger we set when it was held back by the cap yesterday; rich valuation versus fair value ranks it ahead of ASMPT for the last slot. OPS: T6 promotion 'REDUCE cv>=65' fired (cv76); MoS -5.35 up-rank over 0522 (-4.07) despite smaller bleed 139k vs 158k; x 85.46% = (lot 500); residual 500 stop 61.55. · news
0522ASMPT168.10NO ACTION168.10152.83167.10 (-0.6%)179.38 (+6.7%)170.97 (+1.7%)ASMPT turned to a strong sell-and-reduce signal after two no-trade sessions, but closed +5% on the iPhone 18 launch day with a mildly positive 12-week view; held back by the three-sell cap. OPS: cap overflow #4; promotes on a second consecutive settled REDUCE cv>=65 OR settled close < 152.83. · news
0823Link REIT37.02NO ACTION37.0236.7437.14 (+0.3%)37.45 (+1.2%)36.59 (-1.2%)Link REIT keeps a stable strong sell-and-reduce signal with a negative 12-week view, but its dollar exposure is the smallest of the flagged names, so it sits behind the cap. OPS: cap overflow #5; 09-17 SELL 1,400 unexecuted; promotes on settled close < 36.74. · news
0700Tencent419.00NO ACTION419.00416.17417.23 (-0.4%)412.61 (-1.5%)407.89 (-2.7%)Tencent broke down to close at the day's low with a negative 12-week view, but the sell label appeared only at the settled close after five intraday AVOID prints, so it waits for confirmation. OPS: late-flipped REDUCE; cap overflow #6; promotes on settled close < 416.17 OR a second REDUCE print. · news
0005HSBC Holdings161.60HOLD159.80155.31n/an/an/aHSBC's stop-break sell was issued for the third and final time and not executed; the signal has since softened to AVOID and the break narrowed, so the sell is retired to a watch line. OPS: HK-11 retirement (signal decay NT->AVOID 63, not REDUCE); close 161.60 vs 163.18 (0.52 ATR); re-arm settled close < 155.31 OR REDUCE cv>=65; model stop 167.73 > close refused (P6). · news
3750CATL507.00HOLD507.00486.40n/an/an/aHOLD - WATCH 486.40; re-arm settled close < 486.40 OR REDUCE cv>=65.
2888Standard Chartered245.00HOLD245.00236.74n/an/an/aHOLD - stop 236.74; intraday AnticipationUp_VCP HOLD 84-97 never printed BUY-ANTICIPATE.
7709XL2CSOPHYNIX43.30HOLD43.3034.40n/an/an/aHOLD - stop 34.40; NO TRADE x1 'Consensus conflict + low conviction'; 2x leveraged-ETF rule unmet.

Outcome & track record

Accuracy at the time of this record.

231 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.

This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.