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 |
|---|---|---|---|---|---|---|---|---|---|
| 0992 | Lenovo Group Limited | 37.58 | SELL 30% | 37.58 | 32.95 | 35.90 (-4.5%) | 31.98 (-14.9%) | 53.55 (+42.5%) | Banking part of a 20% three-day run: Lenovo jumped 9.5% to a new high on the heaviest volume of the move, and the model flipped from a bullish setup to an overbought-reversal signal with momentum collapsing (pillar at RSI 72; shares trade about twice fair value, so trim a third and trail the rest. CLAUDE.md s9 origination = RSI extension at deteriorating momentum (late-flipped bearish family, cv86 bullish -> cv67 bearish). Not PROFIT_ARMED (Gain_ATR 2.93 < 3.0) so not a profit-take tier; 30% signal-degradation tier. MoS -1.03 > -3 -> no tier bump. G1 n/a (no longer fresh breakout), G3 passes (signal bearish). 30% x = (6 x). Residual 30,000 trail 31.15 -> 32.95 (HS-19/HS-31). Pre-commit: 2nd consecutive bearish-family print -> trim to 15,000; settled close < 32.95 -> exit residual. Reprice if the 09-21 open gaps >1.5%. · news |
| 2382 | Sunny Optical Technology | 67.05 | HOLD | — | 67.02 | 69.13 | 73.99 | 74.72 | Hold on its stop: Sunny closed 67.05, three cents above the 67.02 stop, and conviction recovered to 54, clearing the sub-50 watch. Intraday low 66.80 probed the trail a 4th time but L4 settled close governs. Exit 100% on settled close < 67.02 or bearish-family flip. · news |
| PORTFOLIO | AI - HK Semiconductors | — | WATCH | — | — | n/a | n/a | n/a | One trade tonight: trim a third of Lenovo after a 20% three-day run flipped the model to an overbought-reversal signal; hold the rest on a stop raised to 32.95. Sunny Optical holds three cents above its stop. No buys: YOFC still fails the quality screen. Book HK (+5.70%); cash HK -> ~HKafter the trim. Step 8a skipped (batch). |
Outcome & track record
Accuracy at the time of this record.
20 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 →
-0.097 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.