Hong Kong — End-of-Day Verdict
1 DISPOSE (2513 FULL EXIT 1,000 @ ~1219.00 MKT - frees HKthe same broken name +36.9% higher than yesterday's recommendation) + NO ACQUISITIONS (no bullish actionable row in a scan that covered only tickers). 0 stop breaches among names that printed; unverifiable (degraded scan). Both 07-20 queues withdrawn (0857 cv52; 9618 absent). Trail-raises: 1347.00, 0522 146..50. HK -> HK.
Recommendations
0 to acquire · 1 to dispose
| Ticker | Name | Close | Action | Action 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 |
|---|---|---|---|---|---|---|---|---|---|
| 2513 | KNOWLEDGE ATLAS | 1219.00 | SELL ALL | 1219.00 | — | 1243.02 (+2.0%) | 1212.10 (-0.6%) | 1241.33 (+1.8%) | Closing the book's largest and most broken position into an unexplained +36.9% bounce. The model has printed a reduce label for nine consecutive snapshots and strengthened it to STRONG SELL today at the top sell rank, while the price remains 21% below its 20-day and 16% below its 50-day trend lines - the bounce has not repaired anything. Decisively, the forward view is now dead: the four-week estimate is slightly negative and the twelve-week estimate is +1.8%, versus +9.5% yesterday, so there is nothing left to wait for. The name has no fair-value coverage at all and a 52-week range of, and the position is still 25% underwater against cost even after this move. Operational nuance: escalated from the model's 85.46% portion to a full exit - a stable multi-print REDUCE is a full-exit basis under CLAUDE.md section 9, and this is a signal exit, not a profit-take. Order is MARKET at the open, not a limit - this card has now been proposed for five consecutive sessions and must not be stranded again (L3/HK-5). Expect slippage: the name has moved >15% intraday on four of the last five sessions. L7: also sits in hktech - execute ONCE. · news |
| 1347 | Hua Hong Semiconductor | 168.50 | HOLD | — | 145.00 | 170.14 | 164.56 | 184.55 | Up 17.9% on the session and profitable against cost for the first time, at +5.3%. The forward twelve-week view is alive at roughly +9.5%, so there is no exit case, and the model has printed no-trade for thirteen straight snapshots, so there is no entry case either - the right action is to protect the recovery, not to act on it. Operational nuance: this position is technically profit-armed with a deterioration tick fired (repeated no-trade prints), but the profit-take is SUPPRESSED because the arming metric is defective book-wide - the real gain is 0.39 ATR against a 3.0-ATR arm, i.e. a position that just got back to break-even, not a winner to harvest (systemic finding #2). Trail raised from.00, just under the session low, which is also the correct posture into SK Hynix results next session. L6: the gap is explicitly not added to. Still the book's top exit-watch - a fresh breakdown-family SELL print or the twelve-week estimate turning negative means dispose immediately. · news |
| 0522 | ASMPT | 171.70 | HOLD | — | 156.50 | 177.74 | 178.15 | 200.98 | Held into its own earnings print after a 6.5% session that cut the loss against cost from 17.9% to 12.6%. The twelve-week view is the most positive in the book at roughly +17%, the bearish label that briefly appeared on 07-17 never confirmed, and valuation cannot originate a sell - so there is no case to reduce ahead of the numbers. Operational nuance: catalyst-aware hold, no pre-trim into a binary two sessions away; the model's stance is to add after the print, not before. Trail raised from 146..50, just under the session low, which banks most of the move if the print disappoints. Only a confirmed lower high or a decisive stop break changes this beforehand. · news |
Outcome & track record
Accuracy at the time of this record.
111 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 →
-0.283 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.
21 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.