Recommendations
0 to acquire · 0 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 |
|---|---|---|---|---|---|---|---|---|---|
| 2318 | AAC TECH | 56.65 | WATCH | 54.10 | 52.71 | 54.49 (+0.7%) | 55.39 (+2.4%) | 50.79 (-6.1%) | The book's only buy signal is a pullback entry the model itself does not expect to pay: both the 4-week (55.39) and 12-week (50.79) projections sit below today's 56.65 close, and the shares have already run 4.7% past the 54.10 entry the setup was built around. Conviction is 58 against a 65 floor and has stopped improving, while the reward-to-risk on the printed levels is only 0.93 - risking 1.39 to make 1.29. Nothing in the news flow or the valuation layer argues otherwise, so we pass again. Fourth consecutive session rejected on the same three grounds. Learnings applied: HT-4 (forward view screened before the conviction floor), HT-3 (printed R:R is a config artifact - use an independent forward+stop check), L1 (favour sound pullbacks, not extended ones), note B (HK falling-knife pool). NA_CCY -> val_adj 0, quality gate off. Extended ED -2.28 so even a pass would have been QUEUED-only at 54.10. RE-ARM: cv>=65 AND Target_4w/Target_12Week both above close AND entry not extended. · news |
| 9618 | JD-SW | 119.20 | WATCH | 119.20 | 118.20 | 121.14 (+1.6%) | 125.65 (+5.4%) | 127.59 (+7.0%) | JD is the only name in the book that looks structurally right - the shares trade below our estimate of intrinsic value on a passing quality screen, and both the 4-week (+5.4%) and 12-week (+7.0%) projections point higher from today's 119.20 close, with the price sitting right at the entry rather than extended above it. What is missing is the signal itself: the engine prints WATCH, not BUY, at conviction 53 against a 65 floor, and the suggested stop is only 1.00 wide against a 3.23 average daily range - too tight to survive ordinary noise. We wait for the setup to confirm rather than anticipate it. Learnings applied: L1 (the FailedBreakdown_Up family is weak here, ~0.25 hit / ~60% stop-first - do not chase), HT-4 (a positive forward view is necessary but not sufficient), HT-3. Trail NT0->WATCH45->NT0->WATCH53: improving but choppy, no BUY print in four sessions. Same 0.31-ATR knife-edge stop geometry that stopped 0992 out twice. RE-ARM: fresh BUY print at cv>=65 with the positive forward view intact AND a stop at least ~0.5 ATR wide. · news |
| — | AI - HK Tech | — | NO ACTION | — | — | n/a | n/a | n/a | No action today: the portfolio stays entirely in cash. Across all 21 names the scan produced a single buy signal, and it is one the model's own forecasts contradict - projected lower over both the 4-week and 12-week horizons. Ten names are flagged as active breakdowns, and the one attractively valued candidate has not yet given a buy trigger. With a Federal Reserve decision, three chip-sector earnings reports and a Chinese policy meeting all landing inside the next four sessions, holding the full HKin reserve is the position. Eleventh consecutive 100%-cash session. Sell pool empty by construction (zero holdings). No pending or queued orders outstanding; nothing to reprice or expire. Monitor clean (CASH no_stop only). |
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 →
-1.015 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.
22 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.