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 28 Oct 2026, 16:00:00 GMT+8

Hong Kong — End-of-Day Verdict

EOD 2026-10-28 (hk)

Recommendations

2 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
0068MANYCORE TECH3.77BUY — QUEUED @3.643.643.234.03 (+10.7%)3.81 (+4.7%)4.30 (+18.1%)STRONG BUY 90 ReversalUp_Oversold for 8 sessions; today's +20.6% close-at-high is the reversal confirming, so we queue a no-chase limit 0.25 ATR under the model entry rather than buy the high. Half size (R7). Stop 3.23 (close - 1 ATR; model 2.18 refused, HK-12). P5: fifth consecutive queue - an unfilled expiry demotes to WATCH, no further reprice. · news
2382Sunny Optical Technology65.80BUY — QUEUED @65.9165.9158.8365.19 (-1.1%)66.04 (+0.2%)67.99 (+3.2%)Fresh STRONG BUY 84 20-day breakout on a quality name trading below fair value (MoS +0.13, F-Score 8). First settled print, so HK-1 applies: buy-stop that fills only on a push through 65.91, half size (overrides the 1.25x UNDERVALUED modulator). Withdraw on conv < 65 or an AVOID settle. · news
2513KNOWLEDGE ATLAS571.50SELL 85.46%571.50473.06609.94 (+6.7%)645.42 (+12.9%)629.25 (+10.1%)Live STRONG SELL-REDUCE on every print (Sell_Rank 1) in the book's most reliable sell cell; selling the +3.8% bounce, still below the 580.67 stop and -65% vs cost. Residual stop 473.06. Estimator disagrees (P2 slice, down-weighted). · news
0005HSBC HDGS(USD0.50) HK O'SEAS135.60SELL 50%135.60127.29137.14 (+1.1%)139.91 (+3.2%)139.07 (+2.6%)18th settled session below the 155.31 stop and 4th close below EMA after a Q3 miss; yesterday's SELL-REDUCE reverted to NO TRADE on a green day, which does not withdraw a sell (HK-EOQ-2). NoTrade|sell is the book's best cell (+8). HK-11 escalated form: if unrecorded again, retire to WATCH (re-arm: settled REDUCE or close < 127.29). Residual stop 127.29. · news
0700TENCENT387.60SELL 50%387.60368.18388.87 (+0.3%)377.19 (-2.7%)385.73 (-0.5%)Fresh STRONG SELL-REDUCE on all three of today's prints plus the L2 combo (7.7% below the 420.11 stop with a negative 12-week view); fairly valued, so valuation neither amplifies nor argues down. Engine 85% trimmed to one lot (R7). Residual stop 368.18. · news
7709XL2CSOPHYNIX25.42HOLD—18.5026.2124.7228.34SSR 76 on 14 straight prints but SK hynix printed a record Q3 (OP beat, KRW34tn returns) and the ETF ran +21.9%; news overrides a sell into the print tonight. SELL 900 (2x ETF 50%) on a settled close < 23.40 or any settled SSR after 10-29. Stop raised to 18.50 (close - 2 ATR). · news
0981SMIC47.80HOLD—41.4948.4849.2955.71Settled REDUCE faded to HOLD 71 on a +5.4% bounce; HOLD is not a bullish actionable print so the sell case stays open (HK-EOQ-2). SELL next slot. Stop_after 41.49 (model). · news
1347Hua Hong Semiconductor70.00HOLD—58.3372.3377.5791.76HOLD 72, +8.4% bounce, still 30% below the recorded stop. Case open; SELL next slot. Q3 ~11-06. · news
0522ASMPT118.30HOLD—104.01125.52127.66131.38HOLD 84 on the Q3 day (C 118.30, -2.4%); rising conviction but not a bullish actionable print. Case open; SELL 500 next slot, retires only on a settled BUY/BUY-ADD. · news
2888STANCHART219.80HOLD—199.35221.90218.05220.77Q3 day +7.6% back above EMA; NT x4, 12wk close so L2 lapsed. SELL re-arm: settled 12wk < close or a REDUCE label. Stop_after raised to 199.35 (2 ATR). · news
3750CATL346.40HOLD—317.13359.12363.57403.95HOLD 67 at the settle after SSR intraday; 12wk > close, re-arm (settled REDUCE >= 65 or 12wk < close) not met. Trail raised to 317.13. · news
0823LINK REIT39.08HOLD—38.1939.0339.1638.11NT; 12wk 38.11 < close so L2 is armed: a settled close below 38.19 triggers a sell. · news
0939CCB - H SHS9.92HOLD—9.639.929.9510.16BUY-ADD faded to HOLD 66; buy-stop withdrawn. Stop 9.63 (+3.0% cushion). CCB Q3 ~10-29/30. Re-queue on a settled BUY-ADD >= 65. · news
2318Aac Technologies Holdings48.38NO ACTION48.3847.3347.82 (-1.2%)47.77 (-1.3%)49.15 (+1.6%)BUY 70 at the settle after AVOID 47 intraday (flip-flop); estimator negative at 1w/4w and the ticker/name mismatch (P8(b)) is unresolved. Re-arm: two settled BUY prints with non-negative estimates. · news
0772CHINA LIT22.06WATCH22.0621.6922.07 (+0.0%)21.33 (-3.3%)20.09 (-8.9%)BUY 66 FailedBreakdown_Up_20D (chase cell -5) with val_adj -10 -> adj 51, below floor; quality gate failed on a new entry and 12wk 20.09 < close (falling knife). · news

Outcome & track record

Accuracy at the time of this record.

314 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 →
-0.640 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.