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 |
|---|---|---|---|---|---|---|---|---|---|
| 0992 | Lenovo Group Limited | 30.56 | HOLD | 30.56 | 28.80 | 31.59 (+3.4%) | 34.00 (+11.3%) | 43.55 (+42.5%) | Holding Lenovo, doing nothing. We bought back this morning at HKwhen the stock traded through the level we had set as the re-entry trigger, and it closed the day at HK — a little over 1% underwater on day one, which is noise. The signal cooled from a buy to a watch as momentum eased, but nothing that matters actually broke: the share price is still above its 20-day, 50-day and 200-day averages, all three of which are rising, the trend reading is unchanged at bullish, and the engine flagged no warning of any kind. On value the stock screens as fairly priced with the quality checks passed, so there is no valuation case pushing us out either. There is no reason to add at this conviction level and no reason at all to sell. Ops: WATCH cv55 (from BUY 71) on FailedBreakdown_Up_20D; HS-4 — a single soft print on a held name is noise, require 2 consecutive. Stop HELD at 28.80 (1.02 ATR below close, HKopen risk, 0.93% of book from cost) and deliberately NOT raised to the model's 30.04, which is 0.30 ATR — degenerate-tight per Systemic #3; HS-3(a) forbids adopting a drifted-down stop, not adopting a nonsensically tight one. ADR-0012 not armed (Gain_ATR −0.20, T12_Progress −2.8%); ADR-0020 erosion 0.0% off a Peak Stop set today. 12wk 43.55 = 1.42507 x close = the clamp rail, ninth session — zero forward information. 4wk carries hit_4w 0.000 on this cell (n=6). Scan row printed Held=N (CSV written 4s before the executor logged the fill) — read from the portfolio JSON per HS-1, all position metrics hand-derived. Re-arm to ADD: conviction back >=65 on a bullish-family label with the trend stack intact. · news |
| — | AI - HK Semiconductors (book-level) | — | NO ACTION | — | — | n/a | n/a | n/a | No trades today. The book bought its Lenovo position back this morning at HK — the one order that was resting — and after that fill there is nothing further worth doing. Of the twelve names in the mandate, six carry outright bearish signals we cannot act on in a long-only book, four are flagged no-trade with the engine's own pillars in conflict, one is the position we now hold, and the twelfth is a stock the model likes but that fails our quality screen and would have to be chased 4.5% higher to buy. The cheapest name on the list, Sunny Optical, has had no buy trigger for four sessions and cheapness alone never starts a position here. So we hold what we own, keep the risk line where it is, and leave 86.5% of the book in cash waiting for a setup that clears the bar. Ops: highest adjusted conviction in the book is 64 (1347) and it is a bearish-family AVOID, unbuyable at any score; highest bullish-family adjusted is 6869 at 48 vs the 65 floor. Zero sell-origination classes fire on 0992 (signal / ADR-0012 / ADR-0020 all negative). ANTICIPATE slot not eligible — no BUY - ANTICIPATE print in the last 3 snapshots. No open GTC orders after tonight. Book HK = +13.31% vs the HKseed; 13.5% invested. |
Outcome & track record
Accuracy at the time of this record.
14 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 →
-0.138 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.
49 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.