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 |
|---|---|---|---|---|---|---|---|---|---|
| D05 | DBS Group Holdings | 76.91 | WATCH — queued order lapsed | — | — | n/a | n/a | n/a | Queued buy @77.20 lapsed — closed 76.91 below the level; awaiting reprice at the next end-of-day run. Reconcile line - the 2026-08-31 DBS add EXECUTED. The session high of 77.78 traded through the 77.20 buy-stop and input/sgotrportfolio.json now reads at an average cost of 76.1606, up from 7,700. This is the only executed acquisition anywhere in the HK/SG estate tonight. It is also the control case for the executor outage: the IDENTICAL card in the sg book - same name, same 77.20 trigger, same session - did NOT execute and is now flagged UNRECONCILED under ADR-0019. Same decision, different execution layer. This book's Auto-Executor last ran 2026-09-01 and is one of only three in the estate that is not stale. Stop raised 75.43 -> 76.59 (live model level, above the carried value). NOTE: the position is now S = 59.8% of book NAV, exactly on the 60% max_position_pct cap - no further D05 adds are possible. |
| S68 | Singapore Exchange | 24.95 | NO ACTION | 25.07 | 24.58 | 25.46 (+1.6%) | 26.37 (+5.2%) | 27.37 (+9.2%) | Singapore Exchange is the book's only buy candidate and we are passing on it, because every way we value the business says the shares are expensive: discounted cash flow puts fair value near 18 and the no-growth earnings power value near 8, against a 24.95 market price. The signal itself is not strong enough to override that - conviction has collapsed from the model's ceiling to a mid-range reading in three sessions. We would rather hold the cash. OPERATIONAL: raw cv60 is ALREADY below the 65 floor before valuation; val_adj -9 from MoS_FV -1.878 takes adj to 51, fourteen points short. Critically this is NOT the saturated -10 that EPV-anchoring produces on REIT rows - DCF 17.97 and EPV 8.26 BOTH sit well below the close, so all three methods agree and the haircut measures something real. Stability poor: STRONG BUY cv100 -> WATCH cv63 -> NO TRADE cv0 -> BUY cv60 over four sessions. The 08-28 EOD already withdrew an S68 queue @24.80; re-issuing three sessions later on a weaker print would be churn. Size modulator would have been 0.75x regardless. Horizon: SGX August market statistics ~09-11, two-sided +/-2%. No Est_* columns on this book - horizons above are Step 7 fallbacks at f=0.30. RE-ARM: a BUY/STRONG BUY reprint clearing cv74, enough to survive the -9 haircut with room. Ledgered optional/direction:none so the counterfactual grader prices the decline. |
| O39 | OCBC Bank | 31.34 | HOLD | 30.65 | 30.52 | n/a | 32.32 (+5.4%) | 40.30 (+31.5%) | OCBC is up 9.5% and the profit flag is genuine here - this position has a real, verified behind it - but nothing has deteriorated. The model still sees meaningful upside over twelve weeks, conviction slipped only marginally, and no warning signal has joined the profit flag. The rule in that situation is to raise the trailing stop and keep riding, not to trim. OPERATIONAL: ARMED (Gain_ATR 5.37 on a REAL Avg_Cost 28.63) but NOT FIRED - all four ADR-0012 ticks checked, none fires: (a) PROFIT_ARMED is the only code, no second warning; (b) conviction is -8, short of the -20 threshold; (c) Est_12W 40.30 >> 1.02 x 31.34 = 31.97, forward view emphatically alive; (d) not NO TRADE. Armed-without-a-tick is a MANDATORY trail-raise, never a trim. Trail HELD at 30.52 - the 2.0x ATR chandelier computes to 30.33, BELOW the carried level, and a trail never falls. Unlike the hk and sg books, PROFIT_ARMED here is trustworthy because Avg_Cost is populated. FLAG: this book's Est_12W of 40.30 (+28.6%) for O39 differs from the sg book's 32.63 (+4.1%) on the identical close - a 24-point divergence, systemic finding #1. |
| D05 | DBS Group Holdings | 76.91 | HOLD | — | 76.59 | n/a | 79.05 | 90.74 | DBS was doubled in size at the open today and the position now stands at. The signal has settled back to a plain hold rather than a buy, the forward view remains constructive, and the scheduled-events read is positive for Singapore banks into the September Fed meeting. We hold and lift the risk line under the enlarged position. OPERATIONAL: the position is now S = 59.8% of book NAV, EXACTLY on the 60% max_position_pct cap - NO FURTHER ADDS ARE POSSIBLE, flagged so the next run does not queue one. Stop raised 75.43 -> 76.59 (live model level, above the carried value). Not profit-armed (no Exit_Warning printed). Horizon: bank leg of the hawkish carry-in, direction UP [-1.0,+2.5], with NFP 09-04 and US CPI 09-11 both two-sided +/-2% ahead. FLAG: this book's Est_12W of 90.74 (+18.0%) differs from the sg book's 80.05 (+4.1%) on the identical close - a 14-point divergence, systemic finding #1. |
| — | sgotr | — | NO ACTION | — | — | n/a | n/a | n/a | No new action - the session's real event was a fill, not a decision. The 08-31 DBS buy-stop executed at 77.20, doubling that position to and taking it to 59.8% of the book, exactly on the concentration cap. The only buy candidate, Singapore Exchange, is declined fourteen points below the floor on a valuation haircut that all three methods agree on. No holding printed a sell label, and OCBC - the one genuinely profit-armed position, on a real - has no deterioration tick, so it gets a trail-hold rather than a trim. Two stops move up, nothing else. NOTE: this book's healthy Auto-Executor (last run 2026-09-01) is the control case proving the estate's dropped cards elsewhere are an execution defect - the identical D05 card in the sg book did not execute. |
Outcome & track record
Accuracy at the time of this record.
35 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.
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.