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

HK Tech — End-of-Day Verdict

EOD 2026-09-16 (hktech)

Recommendations

0 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
0992Lenovo Group Limited33.80HOLD33.8030.7837.28 (+10.3%)45.39 (+34.3%)48.16 (+42.5%)Lenovo jumped 8.3% to 33.80 on heavy volume and the engine upgraded it to a 52-week breakout (conviction at fair value with the book's top quality rank, so the winner is held through FOMC and the iPhone 18 launch. Stop held 30.78 (HT-28 trail min(chandelier 36.16-3x1.963=30.27, close-1.5ATR 30.86) < carried; never lowered; scan Stop 29.37 ignored per HT-25); cushion now 1.54 ATR / 8.9% (HT-39 condition cleared). Not ADR-0012 armed (Gain_ATR 2.40 < 3.0; T12_Progress prints 70.18 frozen, hand 24.7%). RSI_DIV present but no sell class: unarmed, MoS -0.69 > -3 so no 9c elevate, G3 bullish signal. T12 48.16 = clamp ceiling (HT-27) n/a and exceeds DCF 45.64. f=0.30 (calib_1w -0.293); 1wk/4wk record-only (HT-44), 4wk target overshoots Est_High 36.14 (HT-23). · news
0992Lenovo Group Limited33.80NO ACTION33.3030.7836.93 (+10.9%)45.39 (+36.3%)48.16 (+44.6%)The engine asks to add to Lenovo after an 8% one-day pop, but it is a single print carrying an RSI divergence, the honest reward-to-risk is below 1 and the order executor has been offline since 09-08, so the add is withheld rather than queued. Adj 79-3=76 clears 65, but: HT-46 executor stale 6 sessions (no executable card may be issued); HT-7 single BUY-ADD print after HOLD/54; HT-23 R:R (min(45.39, Est_High 36.14)-33.30)/(33.30-29.37)=0.72 < 1.5; chase rule EDA -0.25 with close 33.80 near high 34.00; HT-18 add above last fill 31.75. Hypothetical model size 58.23% x = 9,317 -> (lot 2,000) = HKat 33.30, NOT authorised. Re-arm = executor run current + 2nd consecutive BUY-ADD print + RSI_DIV cleared + honest R:R >= 1.5, priced at the live Entry_Price. · news
2513Knowledge Atlas (Z.AI)720.00NO ACTION720.00406.34n/a947.51 (+31.6%)410.40 (-43.0%)Z.AI flipped from a bearish AVOID to STRONG BUY in one session on an oversold bounce, but it is still far below its 20- and 50-day averages with a negative 12-week view and a stop 44% away, a classic falling knife, so no entry. HT-43 hard veto (AVOID/58 prior session, AVOID/81 two sessions back); HT-4 fail (close 720 < EMA20 947.5 / EMA50 1097; T12 410.4 = 0.57 clamp floor); HT-45 stop 3.40 ATR outside band; honest R:R (min(947.51, Est_High 936)-720)/313.66 = 0.69; ATR 12.8% of price; HT-6 placement overhang context; HT-46 executor stale. Valuation NA (Quality_Pass False, rank 10). Re-arm = >=2 consecutive bullish prints + close back above EMA20 + stop inside [1.0, 2.5] ATR. · news
—hktech—NO ACTION——n/an/an/aNo trade today: the two buy prints (a Lenovo add and a Z.AI rebound) both fail the book's stability, reward-to-risk and executor-safety gates, and nothing held has a sell case. 0 ACQUIRE / 0 DISPOSE / 0 ANTICIPATE; HOLD 0992 stop 30.78; cash HK (73.9% of HK). Executor stale since 09-08 (HT-46). HT-12 breadth gauge tripped (9 rising bearish rows).

Outcome & track record

Accuracy at the time of this record.

5 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 →
-0.293 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.