Recommendations
1 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0700 | TENCENT | 490.40 | BUY — QUEUED @496.28 | 496.28 | 446.13 | 526.37 (+6.1%) | 596.58 (+20.2%) | 492.98 (-0.7%) | Tencent has broken out to a fresh 20-day high on heavy volume and is the highest-ranked buy in the book, and the entry is a buy-stop set above today's close - so the order only fills if the move keeps going, never on weakness. The business case supports the tape: Tencent has been buying back its own shares almost every trading day since mid-May (over HK$9bn in June alone, the biggest month of 2026) while doubling AI investment to more than RMB36bn, and it is recycling capital out of stakes like Kuaishou into generative AI. It is not a bargain - our valuation reads the shares as pricing in that growth already - but it is one of the highest-quality balance sheets in the book (F-Score 8, third-ranked on quality), and the risk is defined by a stop 10% below entry for a 2:1 reward-to-risk. We are taking a deliberately half-sized position because Tencent reports Q2 results on 12 August, inside the holding window. | OPERATIONAL: half model slot (HK -> @496.28 = HK7.4% of book). 0.5x discretionary haircut for L1 breakout-family discount + BreakoutUp_20D|buy cell 0-for-2 (report-only at n=2, so expressed as size, bias stays 0) + single-print signal off a NT0->SB79 whipsaw + own Q2 earnings 2026-08-12 and TME Q2 08-11 inside the horizon + EMA200 504.61 overhead. HT-4 passes but the 12wk leg is the weak one: T12 492.98 is +0.53% vs close yet -0.67% vs the 496.28 action price - all positive expectancy sits in the 4wk leg. ED +0.36 = not triggered, no chase. Stop 446.13 = 3.08 ATR, risk HK = 0.75% of book. f=0.30 per L5 (calib_1w -0.814 degenerate, 6 graded < 10). T4 596.58 exceeds Est_High 500.21 (artifact - systemic finding #2); T12 492.98 exceeds DCF anchor 481.75. HT-6 checked and clear - buybacks, not a placement. If filled, the hold-through-earnings decision belongs to the 08-11 EOD run. Reprice if the 08-04 open gaps >~1.5% (L8). · news |
| 9988 | BABA-SW | 125.20 | WATCH | 121.54 | 103.35 | n/a | 157.91 (+29.9%) | 123.29 (+1.4%) | Alibaba is breaking out and the price action is strong, but we are not buying it. Our quality screen fails it outright - the lowest fundamental score in the book on revenue growth of under 3% - and the shares already trade well above what we think the business is worth. On top of that the stock has run past the level we would have been willing to pay, so buying here would be chasing. We would rather miss this move than pay up for the weakest fundamentals we track. | OPERATIONAL: hard quality gate - Quality_Pass=False, F-Score 3, Quality_Rank 14/21, Rev_Growth +2.7%; blocks NEW entries by rule and the book holds zero shares so no ADD exemption. Independently fails HT-4: T12 123.29 < close 125.20 (-1.5%). Extended at ED -0.62 (close 125.20 vs 126.00 high) so even absent the gate this would have been QUEUED @121.54, not bought. Second consecutive session rejected while rallying (+7.0% from the 07-31 reject at 117.00) - flagged for the next learnings review, gate NOT relaxed today. no_chase_queue counterfactual n=2 median -3.09% [saved] supports the no-chase half; nothing in sample tests the quality-gate half. |
| PORTFOLIO | hktech | — | WATCH | — | — | n/a | n/a | n/a | One buy, no sells. The book holds only cash, so there is nothing to sell. We are queueing a half-sized position in Tencent that only executes if the breakout keeps running, and keeping 92.6% of the book in cash ahead of a heavy fortnight of Chinese economic data and Tencent's own results on 12 August. Alibaba was rejected on fundamental quality despite an equally strong chart. | OPERATIONAL: HKcommitted (7.4%), HKretained. Dispose pool empty by construction (zero holdings). Anchor 2026-08-03 live settled close (L4). Valuation regenerated this run (was 10d stale). Scorecard graded 6, calib_1w -0.814 -> f=0.30 (L5); no actionable cells (HT-2). Overlay 29d stale. Step 8a NOT run (batch mode). |
Outcome & track record
Accuracy at the time of this record.
6 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 →
-0.814 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.
50 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.