Recommendations
0 to acquire · 1 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 |
|---|---|---|---|---|---|---|---|---|---|
| N2IU | Mapletree PanAsia Com Tr | 1.24 | SELL ALL | 1.24 | 1.25⚠ | n/a | n/a | 1.08 (-12.9%) | Sell the whole position in Mapletree Pan Asia Commercial Trust at the open. The stop the book set at 1.25 was reached four sessions ago and has still not been reclaimed - the trust traded up to 1.26 during today's session, above that line, and closed back underneath it at 1.24, below every moving average including the 200-day and about three percent above its 52-week low. Tonight the model itself turned decisive: after two sessions of an ambiguous hold reading it issued its strongest sell instruction since the position was opened, ranking MPACT the book's number one disposal at conviction 71 and marking the position as closing. The twelve-week view remains close to thirteen percent below the current price. No fresh news explains the slide; it is a steady de-rating from 1.40 in March to 1.24 now, and the August distribution has already gone ex. The forward calendar argues the same way: US inflation data on the 11th, a Federal Reserve decision on the 16th and a Bank of Japan decision on the 18th all land inside the next two weeks, and MPACT - which funds Japanese offices in yen and owns Chinese retail assets - is exposed to every one of them with no offsetting benefit. Two up sessions and a first improvement in the twelve-week view are the honest counter-argument, but an intraday reclaim that fails is not a reclaim. OPERATIONAL: this is a REPRICE of the 09-02/09-03/09-04 full-exit decision (L3 - not a nineteenth derivation); the 09-04 card's re-derive trigger (open above ~1.248) did not fire, the open was 1.23. Exit basis L2/REIT-2 plus, for the first time, the engine's own sell pool: STRONG SELL - REDUCE 80.07%, Sell_Rank 1, Position_Status CLOSING, Exit_Strategy immediate, Action_Rationale 'REDUCE 80% (target full exit)'. REIT-1 satisfied affirmatively - family is the REIT-1-trusted FailedBreakout_Down_20D, which is also the scorecard's best actionable cell (+6, n=10, hit_1w 0.778). Adjusted conviction 71 + 0 (SGR-1, valuation zero-weighted on this book) + 6 = 77, clearing the 65 floor outright rather than being justified past it as on 09-04. Taken at 100% rather than the engine's 80.07% because a hit-and-broken stop is not renegotiable and this book's documented failure mode is not cutting - counterfactual optional_trim n=47, median wh_4w -4.51%, worse every session measured. ADR-0020 does NOT fire (6.0% erosion vs 15% threshold, unconfigured here). Model Stop_Price 1.19 printed correctly below the close tonight, but the inverted-stop defect has alternated above/below/above/below across four sessions - not resolved. ESTIMATES: Target_Price is NULL on a STRONG SELL row with Sell_Rank 1 (third consecutive session, escalated systemic finding), so 4wk is n/a and the f=0.30 interpolation is unusable; the Est_Low/Est_High band is exactly symmetric again (close +/-2.00%) so its midpoint reproduces the close - 1wk reported n/a with the 52-week low 1.2020 (-3.1%) as the usable downside reference. Reprice if the open gaps beyond ~1.221/~1.259; RE-DERIVE rather than reprice above ~1.259, which would clear both the 1.250 stop and today's 1.26 high. BLOCKING: Auto-Executor last ran 2026-08-03 - 24 trading sessions, 18 consecutive dropped cards, measured outage cost ~SStep 8a learnings review NOT run (skipped by instruction). · news |
| PORTFOLIO | sgreit | — | WATCH | — | — | n/a | n/a | n/a | One disposal, no acquisitions. MPACT is sold in full at the open: the 1.25 stop has been broken for four sessions, today's move above it reversed into the close, and the model has now escalated to its strongest sell reading of the position's life, ranking the trust the book's number one disposal. The twelve-week view still sits about thirteen percent below the current price, and US inflation data, a Federal Reserve decision and a Bank of Japan decision all land within the next two weeks on a trust that funds Japanese offices in yen. Nothing was bought because nothing qualified - seven of eight names printed AVOID and the eighth printed NO TRADE; every name in the book still projects lower over twelve weeks, though every one of those gaps narrowed today. Executing this leaves the book entirely in cash. OPERATIONAL: buy pool empty at source for an eleventh session, so the 65 floor / quality gate / size modulator were never reached; SGR-2 would independently bar all eight on negative Target_12Week. Valuation regenerated tonight (was 10 days stale) - fresh, NA, and zero-weighted per SGR-1. ME8U's re-arm failed in an anomalous way: pillars strengthened (Trend, Momentum, Mostly_Aligned, close above all EMAs) while the signal collapsed to NoSignal cv0 - logged as a definitions-coverage hole, not a bearish read. Overlay stale 64 days; horizon fresh (parent sg fallback, no sgreit_horizon.json has ever been generated). |
Outcome & track record
Accuracy at the time of this record.
20 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 →
-0.043 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.
48 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.