AI · SG Blue Chips — Trades
Every virtual fill this book has made, with the model's reasoning — the fused signal, valuation and news case — behind each. Prices are model fills; quantities are never shown.
Fill history
3 recorded fills.
| Date | Ticker | Name | Side | Fill Px | Signal | Conv | Valuation | Why |
|---|---|---|---|---|---|---|---|---|
| 2026-07-17 | O39 | OCBC Bank | BUY | 28.63 | MomentumContinuation_Up | 68 | OVERVALUED VS RI | rationaleSole surviving BUY in the SG blue-chip complex (Buy_Rank 1, MomentumContinuation_Up conv 71): OCBC riding the record-high SG bank rally with the 1H26 result +28.2% behind it; a healthy business into a rate-supported tape, priced a touch rich (OVERVALUED_VS_RI, MoS -0.59, val_adj -3) so we queue a small pullback rather than chase. Repriced standing GTC from @28.00 (did not fill 07-15) to the current model entry @28.63 (EDATR -0.27, limit below close 28.78 = no chase at RSI 87.0). L8 pending_next_open execute 07-17; reprice if the open gaps >~1.5%. Bank Quality_Pass=False & DCF 25.10 are financial false-fails, non-binding; 12wk 37.04 exceeds broken DCF -> anchor flag suppressed. Size_mod x1.0, ~S (~8.3% book), self-financed. decided @ 28.63 · stop 26.96 · t1w 29.63 · t4w 31.97 · t12w 37.04 |
| 2026-07-16 | D05 | DBS Group Holdings | BUY | 72.42 | MomentumContinuation_Up | 68 | OVERVALUED VS RI | rationaleDBS BUY MomentumContinuation, conv 71 -> adj 68; rate-supported core bank in a confirmed record-high SG bank rally (overlay/news). The 07-14 pullback limit @70.98 never filled (name ran up, not down); conv still 71 (>=65 floor) and expires_on not passed, so REPRICE (not withdraw) to the current model entry @72.42 per the provenance rule. Close 72.98 sits 0.44 ATR above entry (RSI 85.4 extreme) -> a pullback limit, no chase; it fills only on the healthy pullback we want to enter on. ~S (~8.0% of book). Stop 68.58. Bank DCF 52.03 broken -> DCF-anchor flag suppressed (financial, FV=ResInc); Quality_Pass=False is the financial false-fail, non-binding. L8 pending_next_open 07-16; reprice if the open gaps >~1.5% past 72.42. · news decided @ 72.42 · stop 68.58 · t1w 74.72 · t4w 80.09 · t12w 89.06 |
| 2026-07-15 | G07 | Great Eastern | BUY | 18.27 | MomentumContinuation_Up | 89 | OVERVALUED VS RI | rationaleFresh #1 STRONG BUY MomentumContinuation on Great Eastern into a broad SG blue-chip momentum flip; valuation ~fair (MoS -0.18, val_adj -1). Taken as an on-strength buy-stop @18.27 rather than a market chase because RSI 93.5 is a climax reading (avoid post-close STRONG BUY hype not confirmed by next open, CLAUDE.md sec 9) - the stop fills only if the name trades up through 18.27, its own confirmation gate. Half-tranche ( ~S, ~4% of book), discretionary climax haircut; insurer, thinly traded. Stop 17.03. L8 pending_next_open 07-15; expires 07-17. Reprice if 07-15 opens gapping >~1.5% past 18.27. decided @ 18.27 · stop 17.03 · t1w 19.02 · t4w 20.76 · t12w 20.43 |
Learnings in force
What this book's own record has taught it.
Last reviewed 2026-07-18
Favor PullbackBuy_VWAP entries over breakout/FailedBreakdown chases.
`PullbackBuy_VWAP|buy` is the most reliable buy cell (US hit ~0.86); `FailedBreakdown_Up_20D|buy` chases are weak (~0.25, stop-first ~60%) and `BreakoutUp_52W` 4wk targets overshoot +55-75% and mean-revert. On ties prefer the PullbackBuy; discount breakout/FailedBreakdown chases.
Trim on the stop-break + negative-12wk combo; don't wait for the SELL-REDUCE label.
A decisive close below the recorded stop AND a negative 12wk is itself a signal-based exit (CLAUDE.md §9), even while the engine still prints NO TRADE.
Execute the de-risk promptly.
A trim recommended but not executed keeps bleeding; act when a held name closes below stop with a negative 12wk, don't re-recommend the same trim for days.
The settled close is authoritative; don't act on weak opens.
Intraday/BOD prints whipsaw. Flag intraday reads provisional; reserve firm acquire/dispose for the settled-close EOD.
Distrust the model 1-week estimate when `calib_1w` is degenerate.
If the scorecard `calib_1w_fraction` is <=0 or wildly unstable, fall back to f=0.30 for the 1wk interpolation and flag it.
Don't chase post-earnings gaps.
A blowout (e.g. MU +14% AH) often round-trips within days; wait for the pullback to the model entry.
(ARCHIVED for sgotr — ADR-0014 standalone) Same-pool/cross-book shares execute ONCE.
This lesson applied when sgotr mirrored `sg`. Post-2026-07-06 sgotr runs on its own S seed cash with no shared shares, so there is nothing to reconcile here; this book's own cash independently. Retained only as the generic rule for any book that still genuinely shares a pool with `sg`.
EOD recommendations execute at the NEXT market open, not the decision close.
Persist actions as `execution_status: pending_next_open` with an `execute_on` date; action prices are close-refs — reprice/re-validate if the open gaps >~1.5%; the 1wk/4wk/12wk horizons and the scorecard grade from the execution date/price; live holdings/monitor stay unchanged until the JSON is updated post-fill; the next BOD reconciles pending proposals against the actual open.