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 |
|---|---|---|---|---|---|---|---|---|---|
| AWX | AEM Holdings | 9.18 | WATCH | — | — | n/a | n/a | 9.27 | AEM fell 5.7% today and dropped straight through the stop level of Friday's signal - the setup we declined would have been stopped out on its first session. There is no signal tonight, the stock fails our quality screen, it is priced well beyond our fair-value anchor, and the model's twelve-week view has shrunk to about 1% above the price. OPERATIONAL: NO TRADE cv0; recomputed gate FAIL spread (range 4.47% > 3.00%, turnover S). 09-11 refusal (WATCH cv62 entry 9.73 / stop 9.50) graded vindicated session 1: open 9.57, low 9.16, close 9.18. QPass False; val_adj -10. Re-arm: quality re-rate AND settled favored-cell BUY adj >=65 (L1/MSCAP-1). |
| BN2 | Valuetronics Holdings | 0.95 | WATCH | — | — | n/a | n/a | 0.79 | Valuetronics' oversold bounce signal faded to nothing today, with the price flat and the model's twelve-week view slipping further to about 17% below the price. It still fails our quality screen, so there is no case to own it. OPERATIONAL: NO TRADE cv0, Indeterminate consensus; recomputed gate pass (range 2.63%, S). RSI 27.5. 09-11 refusal (WATCH cv58 entry 0.95 / stop 0.93) flat/undecided session 1 (low 0.945, close 0.950). MSCAP-47 pattern (ReversalUp_Oversold + deeply negative T12) resolved to NO TRADE. Re-arm: QPass True AND settled favored-cell BUY adj >=65. |
| PCT | PC Partner Group | 3.08 | WATCH | — | — | n/a | n/a | 3.83 | PC Partner keeps the only strong forward view on the book (about 24% upside over twelve weeks), passes our quality screen and trades near fair value, but the model produced no buy signal because today's price range was too wide. It goes ex-dividend on Wednesday, and we will check that the dividend adjustment does not distort its signals before trusting any new print. OPERATIONAL: NO TRADE cv0; recomputed gate FAIL spread (range 3.57% > 3.00%, turnover S). Ex-div SGD 0.10 on 2026-09-16 (3.2%). MSCAP-49 check on 09-16/09-17: adjusted vs raw return + dividend; >~1 ATR (0.099) disagreement -> mute on signals until EMA ladder re-converges (MSCAP-27 confirming session). Re-arm (MSCAP-21 AND): settled PullbackBuy_VWAP/MomentumContinuation BUY adj >=65 with printed Entry_Price AND ex-div integrity check passed. |
| 8AZ | Aztech Global | 0.56 | WATCH | — | — | n/a | n/a | 0.32 | Aztech looks cheap on our valuation work, but its chart has been bearish for a week and the model's twelve-week view is around 42% below the price; the bearish signal faded to no signal today. Cheap and still falling is not a buy. OPERATIONAL: NO TRADE cv0 (was AVOID FailedBreakout_Down_20D cv46), Conflicted consensus; recomputed gate pass (range 2.70%, S). SGM-4b/SGM-5: bearish prints and cheapness never populate the buy pool. |
| — | AI - SG Mid/Small Cap | — | NO ACTION | — | — | n/a | n/a | n/a | No action tonight - the book stays fully in cash at SNone of the eleven names produced a buy signal: all eleven print no trade, and seven had price ranges too wide for the model's liquidity check on a day when the group fell about 1.9%. Friday's closest setup, AEM, would already have been stopped out. We hold cash because nothing met the standard, not because we predicted the drop. OPERATIONAL: 48th consecutive all-cash session. 11/11 NO TRADE cv0, no Entry_Price on any row, no BUY - ANTICIPATE in last 3 snapshots, dispose pool empty at (MSCAP-3). Recomputed gate: 7/11 fail (5 spread-only, 2 both). Fairvalue fresh (09-11). Scorecard 243 entries, 0 graded, calib_1w None, f=0.30 (L5); counterfactuals n=6 unchanged (MSCAP-29 label inverted, MSCAP-42: no numeric entries tonight so nothing optional-ledgered). Event Horizon parent sg refreshed 09-14, 0 book matches. Overlay stale 71d. Monitor clean. Step 8a NOT run (batch directive). |
Outcome & track record
Accuracy at the time of this record.
0 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.
0.000 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.