This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.

HK Trades Decided by: AI 🤖

AI · HK Semiconductors — 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.

AI · HK Semiconductors is an academic paper portfolio — virtual money, decided by AI and filled by a deterministic auto-executor. Incepted 2026-07-06. Position sizes and account values are never published; performance is shown only as a base-100 Total-Return Index.

Fill history

2 recorded fills.

DateTickerNameSideFill PxSignalConvValuationWhy
2026-07-130992Lenovo Group LimitedBUY23.42PullbackBuy_VWAP84
rationale

Lead acquire for the all-cash ADR-0014 book: 0992 Lenovo prints a 2nd consecutive STRONG BUY cv84 on the L1-favored PullbackBuy_VWAP cell, Buy_Rank #1, with a bullish AI-PC refresh + AI-infra tailwind (news confirms: +137% YTD leadership, Zacks #1 Strong Buy; the pop is momentum not an earnings gap, L6 clears). Reprice/re-queue of the 07-09 limit that never filled (07-10 Low 24.44 stayed above the 23.42 limit all day) -> action price repriced to the live Entry_Price 23.54 (within 0.25 ATR, provenance-clean); entry 23.54 sits -0.53 ATR BELOW the 24.48 close so no-chase holds, fills only on a dip. Valuation blind (val_adj 0, gate off, size x1.0); scorecard has no PullbackBuy cell (bias 0); f=0.30 (calib 0.431 but <10 graded buys, L5). Measured 20% (HK8 lots x 2,000, 18.8% of seed), 81% dry into CPI 07-14 (overlay event-gate). Action price = anchor 07-10 close ref; reprice if the 07-13 open gaps >1.5%. expires 2026-07-15 (anchor +3 sessions); execute on a limit touch from the 07-13 open. · news

decided @ 23.54 · stop 21.26 · t1w 24.87 · t4w 27.96 · t12w 34.88

2026-07-130992Lenovo Group LimitedBUY23.54PullbackBuy_VWAP84
rationale

Lead acquire for the all-cash ADR-0014 book: 0992 Lenovo prints a 2nd consecutive STRONG BUY cv84 on the L1-favored PullbackBuy_VWAP cell, Buy_Rank #1, with a bullish AI-PC refresh + AI-infra tailwind (news confirms: +137% YTD leadership, Zacks #1 Strong Buy; the pop is momentum not an earnings gap, L6 clears). Reprice/re-queue of the 07-09 limit that never filled (07-10 Low 24.44 stayed above the 23.42 limit all day) -> action price repriced to the live Entry_Price 23.54 (within 0.25 ATR, provenance-clean); entry 23.54 sits -0.53 ATR BELOW the 24.48 close so no-chase holds, fills only on a dip. Valuation blind (val_adj 0, gate off, size x1.0); scorecard has no PullbackBuy cell (bias 0); f=0.30 (calib 0.431 but <10 graded buys, L5). Measured 20% (HK8 lots x 2,000, 18.8% of seed), 81% dry into CPI 07-14 (overlay event-gate). Action price = anchor 07-10 close ref; reprice if the 07-13 open gaps >1.5%. expires 2026-07-15 (anchor +3 sessions); execute on a limit touch from the 07-13 open. · news

decided @ 23.54 · stop 21.26 · t1w 24.87 · t4w 27.96 · t12w 34.88

Learnings in force

What this book's own record has taught it.

Last reviewed 2026-07-18

L1

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.

L2

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.

L3

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.

L4

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.

L5

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.

L6

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.

L7

(ARCHIVED for hksemicon — ADR-0014 standalone) Same-pool/cross-book shares execute ONCE.

Applied when hksemicon mirrored hk. Post-2026-07-06 it runs on its own HK seed with no shared shares — nothing to reconcile; own cash independently (HS-1). Retained only as the generic rule for a book that still shares a pool with hk.

L8

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.

This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.