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 |
|---|---|---|---|---|---|---|---|---|---|
| PCT | PC Partner Group | 3.03 | NO ACTION | — | — | n/a | n/a | 3.60 | PC Partner remains the single most attractive name on this book and we still own none of it. It rose another 3.4% today to 3.03 on S of turnover - 62 times our minimum liquidity floor - it screens cheap on our valuation work, it passes our quality checks, and its twelve-week outlook improved again to 3.60, a gain of about 19% and the only positive forward view on the entire book. We did not buy it because our trading engine refused to issue a signal on it for the second session running: the shares swung 3.96% between high and low, above the 3.00% intraday-range cap we apply to Singapore names, so the name is screened out on price volatility rather than rejected on merit. Operationally: gated sessions (range 3.07% then 3.96%) while the shares advanced a cumulative +4.5% off the 2.90 close of 09-03 - the gate is now demonstrably costing this book, see systemic finding 1. range_to_atr 1.12 (an ordinary bar by its own volatility) clears the US 2.0x and HK 3.0x gates comfortably. RSI 59.0, EPV anchor 3.006 vs a 3.03 close (the 31.88 DCF print is a growth outlier at Rev_Growth +38.4% and must never be read as headroom - the shares have now closed above the EPV anchor, so the UNDERVALUED label is thinner than it was). NEWS CAUTION CARRIED: SGD 0.10 cash dividend, ex-date 2026-09-16, now ~7 trading sessions out and worth 3.3% of the close - a re-arm filling into that window takes a mechanical gap the engine will read as a breakdown. Re-arm trigger unchanged: a settled BUY/STRONG BUY at adjusted conviction >= 65, preferably PullbackBuy_VWAP or MomentumContinuation (L1/MSCAP-1 bar on a FailedBreakdown_Up_20D chase even at >= 65); size and stop for the ex-div gap or wait until after 09-16. · news |
| E28 | Frencken Group | 2.40 | NO ACTION | — | — | n/a | n/a | 1.52 | Frencken rose 4.4% today to 2.40, its best session of the window - and the strong sell signal our engine printed on it on Friday has simply disappeared. We flag this against our own record: on 2026-09-04 this name produced the highest conviction reading this book has ever generated (74, a failed-breakout sell), we wrote that the news corroborated a topping read, and the stock then went straight up. We owned nothing either way, so nothing was lost, but the call was wrong within one session and we are recording it rather than quietly dropping it. No new company news explains the move; the standing fundamental picture is unchanged - a 77% ninety-day run to a 36.8x P/E against a 27.1x industry average, with management guiding flat first-half revenue. Operationally: AVOID FailedBreakout_Down_20D cv74 (adj 69) -> NO TRADE cv0 'Liquidity gate failed' on a 5.00% daily range against the 3.00% SG cap, on S turnover (the book's second heaviest). MSCAP-2 recurs - FAIR_VALUE band with MoS -0.972 taking a -5 haircut; treat the band as neutral and lean on the MoS sign. Long-only, : an AVOID never populates the buy pool (SGM-4b) and its withdrawal changes nothing actionable. Forward view still -36.7%. · news |
| 5DD | Micro-Mechanics (Holdings) | 2.65 | NO ACTION | — | — | n/a | n/a | 2.24 | Micro-Mechanics is the one name that produced a fresh, tradeable signal today and it points down, not up. Our engine reads a failed attempt to break out of its twenty-day range with reasonable conviction, our valuation work puts the shares modestly above what we think the business is worth, and the twelve-week outlook is 2.24 against a 2.65 close - a decline of roughly 16%. This is a long-only book holding no shares here, so a sell signal gives us nothing to act on; it simply confirms there is nothing to buy. No dated company news; the most recent item is a February 2026 SGD 0.03 dividend. Operationally: cv67 + val_adj -4 = adj 63, two points under the 65 floor, and the label is bearish regardless (SGM-4b). Only traded (S), so it is thin even on a day it cleared the gate. Quality_Pass True, F-Score 9 - a good business at a full price, not a setup. · news |
| 8AZ | Aztech Global | 0.57 | NO ACTION | — | — | n/a | n/a | 0.32 | Aztech screens cheap and passes our quality checks, and it still gives us nothing to buy. Our engine has now printed a bearish failed-breakout reading on it for a third consecutive session, and the strength of that reading is fading rather than resolving - the shares are drifting sideways around 0.57 while our twelve-week model points to 0.32, a fall of nearly 44%, and company revenue is running 30% below the prior year. Cheapness on its own has never opened a position in this book and does not here. Operationally: conviction decayed across the session; adj 60 (val_adj +5, the largest credit this book issues) now sits BELOW the 65 floor, where on 09-04 it sat exactly at it. RSI 26.6 and rising off a 19.7 low but with no bullish carrier. SGM-5 exactly. Search quotes for 8AZ have been unreliable for this book (0.97 returned against a 0.57 settled close) - trust the scan. Re-arm unchanged: Target_12Week must turn non-negative AND a settled bullish print at adj >= 65. · news |
| S71 | Sunright | 0.41 | NO ACTION | — | — | n/a | n/a | 0.24 | Sunright is the deepest bargain on this book by our valuation work and remains completely untradeable. Around Sof stock changed hands all day and the shares swung 12% between their high and low - there is no way to build or exit a position at a sensible price. The twelve-week outlook is also deeply negative at 0.24 against a 0.415 close. It stays on the valuation watch list and nowhere else. Operationally: MoS +0.559, Quality_Pass True, val_adj clamped at +10 (the maximum) and it still originates nothing - SGM-5. Unchanged on the day. Re-arm: turnover must clear S AND Target_12Week turn non-negative AND a settled bullish print at adj >= 65. |
| — | AI - SG Mid/Small Cap | — | NO ACTION | — | — | n/a | n/a | n/a | No trades today. For the second session running the SGX small-cap semiconductor universe closed broadly higher - Frencken +4.4%, PC Partner +3.4%, AEM +2.0% - and this book, which is entirely in cash, took part in none of it. Not one of the eleven names gave us a buy signal we would act on. The only two tradeable readings of the day were both sell signals on stocks we do not own, and the one genuinely attractive business on the list, PC Partner, was screened out for a second day by our own volatility filter rather than on its merits, while it rose another 3.4%. We are stating plainly that standing aside cost us on both of the last two sessions; the discipline that keeps us out of weak setups is, for now, also keeping us out of a rally, and the volatility filter is the specific mechanism doing it. We are not lowering our entry standard to fix that - we are flagging the filter for review. Operationally: 0 ACQUIRE + 0 DISPOSE + 0 ANTICIPATE. Book 100% cash (S), all 11 names, so dispose and add-to-held are structurally N/A (MSCAP-3). Zero bullish actionable labels and zero BUY - ANTICIPATE prints, so the acquire and anticipate slots are empty by construction. For the first session in this window NO row reaches adj >= 65 in either direction (5DD 63, 8AZ 60). SGM-2 does NOT apply two sessions running - the all-cash posture was a cost, not a risk-avoidance win. SGM-3: the S seed does not lower the floor. 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.