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 21 Sept 2026, 16:00:00 GMT+8

HK Financials — End-of-Day Verdict

EOD 2026-09-21 (hkfin)

Recommendations

0 to acquire · 2 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
2318Ping An Insurance53.75SELL 42.86%53.7551.8453.92 (+0.3%)53.27 (-0.9%)55.50 (+3.3%)Ping An has now printed a bearish signal two sessions running since the fill, and today's STRONG SELL - REDUCE is the first one issued against the recognised position, so the pre-committed half-size trim executes. The 12-week estimate is still above the close (55.50), so the book cuts half rather than the engine's 84.59%. OPERATIONAL: 09-18 pre-commit 'second_bearish_print' (HF-P55 2nd print, half tier; 1,750 tie rounds DOWN per HF-P25, no risk leg) -> SELL market at the 09-22 open. PROFIT_ARMED is a near-cost T12 artifact (Gain_ATR 0.90) and is suppressed (HF-P24). Remaining ride on stop 51.84 (printed 51.74; ratchet-up only). Next: a third bearish print cv>=65 -> SELL; settled close < 51.84 -> SELL 1,000. Close-ref 53.75; reprice if the open gaps >1.5%. · news
3328Bank of Communications8.26SELL 50%8.267.978.21 (-0.6%)8.25 (-0.1%)8.27 (+0.1%)BoCom is up about 7% on cost, but its breakout has lost steam: conviction fell from in one session, an RSI divergence appeared, and the model sees essentially no upside left at any horizon. The book banks half the gain. OPERATIONAL: ADR-0012 profit-take. Armed (Gain_ATR 3.00, T12 99.88%). Ticks fired: (a) RSI_DIV, (b) conviction -33, (c) T12 8.27 < 1.02 x close. That is 3 ticks -> profit_take_2 50% = 750 -> board lot (nearest lot), which is the 09-18 pre-commit. G1 softening does not apply (conv 51 < 80). No valuation amplify (NA_CCY). The remaining 500 (odd lot) hold on stop 7.97; a settled close < 7.97 -> SELL 500. Re-arm buy counter reset to 0. · news
1299AIA Group77.35HOLD 1,40077.3575.7576.84 (-0.7%)78.46 (+1.4%)83.16 (+7.5%)AIA has recovered from Friday's NO TRADE to HOLD at conviction 72 and carries the best 12-week estimate in the book (+7.5%), so it rides. OPERATIONAL: the NO TRADE counter resets. PROFIT_ARMED is a T12-ratio artifact at +0.93% (Gain_ATR 0.43) and is suppressed (HF-P24). Stop HELD 75.75 (printed 74.05); cushion 0.97 ATR. Pre-commit: a settled close < 75.75 -> SELL 800. · news
2888STANCHART246.00HOLD 600246.00236.73243.03 (-1.2%)240.43 (-2.3%)240.45 (-2.3%)StanChart is +7.6% and profit-armed, but nothing has deteriorated, so the book trails rather than trims. OPERATIONAL: genuine arm (Gain_ATR 3.05). No fire tick: conv (-4); tick (c) sits on an inverted T12 (240.45 < close) and is suppressed per HF-2/HF-P50. Mandatory trail-raise: the scan's 2.0xATR trail is 234.61, below the recorded stop, so stop HELD 236.73 (cushion 1.63 ATR). Pre-commit: a settled close < 236.73 with Est_12W < Close -> SELL 200. Flash PMIs 09-23 and the summit 09-24 are hold-through. · news
3968China Merchants Bank52.10HOLD 1,50052.1050.8851.81 (-0.6%)51.26 (-1.6%)51.20 (-1.7%)CMB bounced firmly off its stop zone to 52.10 (+7.1% on cost) with conviction up to 65, so the book holds behind the stop. OPERATIONAL: genuine arm (Gain_ATR 3.27). No fire tick: conv; tick (c) is inverted (51.20 < close) and suppressed. Trail: printed 49.99 is below the recorded stop, so stop HELD 50.88 (cushion 1.16 ATR). Pre-commit: a settled close < 50.88 with Est_12W < Close -> SELL 500. · news
0939CCB - H SHS9.76HOLD 2,0009.769.469.73 (-0.3%)9.66 (-1.0%)9.71 (-0.5%)CCB made a new high for the position (+6%) at conviction 65 with no exit leg firing, so it holds. OPERATIONAL: PROFIT_ARMED came from the inverted T12 (T12 9.71 < close; Gain_ATR 2.78 < 3), so the arm is suppressed (HF-2/HF-P50). Stop HELD 9.46 (printed 9.36); cushion 1.48 ATR. Pre-commit: a settled close < 9.46 -> SELL 1,000. · news
3988Bank of China6.06HOLD 4,0006.065.836.05 (-0.2%)5.97 (-1.5%)6.04 (-0.3%)Bank of China remains the book's best holding at +11.4%, and conviction rose to 68, so it rides behind the profit-protecting stop. OPERATIONAL: genuine arm (Gain_ATR 5.21). No fire tick: conv; tick (c) is inverted (6.04 < close) and suppressed. Trail: printed 5.82 is below the recorded stop, so stop HELD 5.83 (cushion 1.93 ATR). · news
2388BOC Hong Kong Holdings52.40WATCH52.4051.5552.58 (+0.3%)53.05 (+1.2%)52.46 (+0.1%)BOC Hong Kong printed a second consecutive BUY (Buy_Rank 1), but it fails the hard quality screen and the 12-week view is flat, so the book does not open it. OPERATIONAL: quality gate F-Score 4 (Quality_Pass False) blocks new entries. val_adj -1 -> adj 67. Est_12W 52.46 vs close 52.40 (+0.1%). Re-arm when the fairvalue refresh passes quality with 2 BUY prints cv>=65 and Est_1W >= Entry. · news

Outcome & track record

Accuracy at the time of this record.

50 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.

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.