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

HK Financials — End-of-Day Verdict

EOD 2026-09-17 (hkfin)

Recommendations

2 to acquire · 0 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 Insurance52.85BUY — QUEUED @52.9952.9951.8453.07 (+0.2%)51.95 (-2.0%)52.88 (-0.2%)Ping An has sold off about 7.5% in two weeks to its lower volatility band with no bad news, and the model now rates it a top-ranked mean-reversion buy with a tight stop. Its quality screen passes, so we open a half-size position on a limit at the model entry. OPERATIONAL: STRONG BUY cv85 Buy_Rank 1, single print reversing AVOID 60/33/33 -> HF-P55 lower tier x0.5. HF-4 pass (Est_1W 53.07 >= entry); HF-3 pass (Est_12W 52.88 vs close 52.85) but forward view flat (4wk -1.96%) -> payoff rests on Target 55.17 vs stop 51.84 (R:R 1.9). 90.4% x 2,037,751 x 20% = 368,425 x0.5 = 184,213 / 52.99 = (lot) = HKWithdraw if <65 or AVOID before 09-22; 2nd consecutive STRONG BUY -> supersede to full size at the live entry (HF-P54). L8: re-adjudicate if the 09-18 open gaps >1.5% from 52.85. · news
1299AIA Group77.35ADD — QUEUED @77.3577.3575.7577.31 (-0.1%)78.57 (+1.6%)82.27 (+6.4%)AIA printed a second straight buy signal after today's half-size purchase filled at 76.10, and the model's one-week view now agrees with the entry, so we complete the position to its target size. It has the strongest 12-week outlook in the book (+6%). OPERATIONAL: BUY cv68, 2nd print retires the 09-16 HF-4 half-size discount (Est_1W 77.31 vs 77.35 = -0.05%, de-minimis). Scan wrote Held=N (executor race) so sized by hand: target 26.5% x 2,037,751 x 20% = 108,001 less held 61,880 = 46,121 / 77.35 = (lot 200). Stop held 75.75 (model 75.60). MoS_FV NA_CCY non-authoritative. Conviction eased 4 and close sits under EMA200 77.64 -> completion, not a pyramid. HF-P34 same-family exposure carried. Withdraw if <65 before 09-22; L8 reprice on a >1.5% gap. · news
3328Bank of Communications8.18NO ACTION8.187.978.14 (-0.5%)8.28 (+1.2%)8.23 (+0.6%)BoCom is near its 12-week target and shows an RSI divergence, which calls for a small profit-take, but 30% of the holding is below one board lot, so we raise the stop instead and record the odd-lot trim only as a what-if. OPERATIONAL: PROFIT_ARMED (T12 99.39, 12wk 8.23 > close, arm stands) + tick (a) RSI_DIV fired -> profit_take_1 30% = 450 vs lot 1,000 -> rounds to 0 (HF-P25, no risk leg). Counterfactual-only card (not executed) so the grader prices the odd-lot trim (HF-P65). · news
3328Bank of Communications8.18HOLD 1,5008.187.978.14 (-0.5%)8.28 (+1.2%)8.23 (+0.6%)BoCom has reached its model target zone with an early warning sign, so we tighten its stop to today's low to protect the gain rather than sell a sub-lot sliver. OPERATIONAL: armed + RSI_DIV fired but lot-suppressed -> mandatory trail-raise 7.85 -> 7.97 (cushion 1.22 ATR). Conviction (-15, <20). Re-arm pre-commit RESET (ADD print did not repeat). Next tick -> 50% = 750 -> SELL market. · news
2888STANCHART243.40HOLD 600243.40236.73241.31 (-0.9%)240.76 (-1.1%)237.36 (-2.5%)Standard Chartered is holding its gains well above the stop, so the position stays on with a pre-set partial sale if it closes below HK. OPERATIONAL: PROFIT_ARMED suppressed (12wk 237.36 inverted 1.04 ATR, Gain_ATR 2.55); conviction (-15, <20). Stop HELD 236.73 (model 231.80), cushion 1.15 ATR. Pre-commit carried: settled close < 236.73 with 12wk negative -> SELL market (L2/HF-P30). · news
3968China Merchants Bank51.30HOLD 1,50051.3050.8851.08 (-0.4%)50.95 (-0.7%)50.39 (-1.8%)China Merchants Bank dipped below its stop during the day but closed above it, so it is held, with a pre-set partial sale if a close breaks HK. OPERATIONAL: settled close 51.30 (low 50.50) -> L4, not triggered; cushion 0.39 ATR. PROFIT_ARMED suppressed (12wk 50.39 inverted 0.84 ATR). Conviction. Pre-commit carried: settled close < 50.88 with 12wk negative -> SELL market. · news
0939CCB - H SHS9.68HOLD 2,0009.689.469.69 (+0.2%)9.75 (+0.8%)9.65 (-0.3%)CCB is steady and about 5% in profit with no sell signal, so we keep holding with the stop unchanged. OPERATIONAL: PROFIT_ARMED suppressed (12wk 9.65 inverted 0.12 ATR, Gain_ATR 2.22); conviction. Stop HELD 9.46 (model 9.25), cushion 1.01 ATR. Pre-commit carried: close < 9.46 -> SELL market. · news
3988Bank of China5.99HOLD 4,0005.995.836.02 (+0.5%)6.05 (+1.0%)5.98 (-0.2%)Bank of China remains the book's best holding (about +10%) and nothing has weakened, so we keep riding it behind the profit-protecting stop. OPERATIONAL: genuine PROFIT_ARMED (Gain_ATR 4.27), no fire tick (conviction; tick (c) 0.08 ATR below materiality) -> trail. Stop HELD 5.83 (chandelier 5.75, model 5.73), cushion 1.24 ATR. · 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 →
5.000 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.