AI · HK Financials — 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
1 recorded fill.
| Date | Ticker | Name | Side | Fill Px | Signal | Conv | Valuation | Why |
|---|---|---|---|---|---|---|---|---|
| 2026-07-17 | 2888 | Standard Chartered | BUY | 228.63 | BreakoutUp_52W | 90 | — | rationaleStandard Chartered breaks to a fresh 52-week high on rising conviction (WATCH cv64 -> STRONG BUY cv90, Buy_Rank 1, RSI 66.9) — the first clean actionable buy the book has printed since inception, and it fires every leg of the 07-15 re-arm we set for it: cv>=65, actionable buy family, NON-inverted 12wk (Est_12W/Target_12Week 228.87 = +0.9% vs close 226.80), non-extended entry (buy-stop +0.34 ATR). Queued as a buy-stop at 228.63 so it fills only if the breakout confirms above the 226.80 close — self-limiting, no chase. Valuation blind (NA_CCY cross-currency -> val_adj 0, quality gate off); news neutral (constructive wealth-pivot strategy, no fresh catalyst). Sized 0.904 Portion x 2.0M x 20% buy_pct = 361.6k -> ( of 50) ~HK, ~17.7% of book; chandelier trail stop 214.98 (~6% risk). Execute next open 2026-07-17 (L8); reprice if the open gaps >1.5%. CAUTION: the model's own Est_1W 226.85 and Est_4W 225.15 sit BELOW the entry (low-quality-entry flag, carried 07-15) — mitigated by the stop-entry design and cv90; watch once filled. Target_Price 255.94 is a stretch breakout objective far above Est_4W. · news decided @ 228.63 · stop 214.98 · t1w 226.85 · t4w 225.15 · t12w 228.87 |
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 hkfin — ADR-0014 standalone) Same-pool/cross-book shares execute ONCE.
Applied when hkfin mirrored hk. Post-2026-07-06 it runs on its own HK seed with no shared shares — nothing to reconcile; own cash independently (HF-1). Retained only as the generic rule for a book that still shares a pool with hk.
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.