gahow/quant-trading - quant-trading - Local Gitea

gahow/quant-trading

Go to file

Gahow Wang aa24ed8c31 research: auction audit of the overnight sleeve's prices (PASS: 0.2 bp a side)

The overnight sleeve buys at the closing cross and sells at the opening
cross; the backtest used Yahoo open/close and 1 bp a side. On 800 random
nights in 2016-26 (7,856 name-nights), the backtest night return exceeds the
cross-to-cross return by +0.12 bp (SE 0.24, median 0): Yahoo's prices are
the crosses. With the SEC fee, cost is +0.20 bp a side, so 1 bp was
conservative. At the Reg T cap this lifts three_sleeve_overnight to 39%/yr
(MaxDD -27%) and the 12_1 variant to 44%. Live fills at the cross remain
unverified (paper does not run auctions).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-12 21:08:32 -07:00

chore: add skill for codex too

2026-10-02 19:26:16 -07:00

.claude/skills/agent-stock-review

agent review: reject future-dated sources at submit; treat fetched pages as data

2026-10-11 22:24:47 -07:00

chore: untrack data/csi300_history.json

2026-09-29 15:15:31 +08:00

live: record each session's target and its frictionless return; compare shows Ideal and Gap

2026-10-12 18:49:28 -07:00

docs/superpowers/specs

chore: remove pre-lab research and dead strategies; index them in research/ARCHIVE.md

2026-10-09 22:20:59 -07:00

research: auction audit of the overnight sleeve's prices (PASS: 0.2 bp a side)

2026-10-12 21:08:32 -07:00

chore: remove pre-lab research and dead strategies; index them in research/ARCHIVE.md

2026-10-09 22:20:59 -07:00

live: record each session's target and its frictionless return; compare shows Ideal and Gap

2026-10-12 18:49:28 -07:00

fix(backtest): settle delisted US holdings (engine v3), PIT membership before 2011, registry causality test

2026-10-10 00:21:49 -07:00

.env.example

refactor: wire web to the in-repo engine and shared data dir

2026-09-25 11:42:35 +08:00

.gitignore

feat(research): Tiingo backfill of delisted names; honest PIT panels

2026-10-08 09:48:05 -07:00

.python-version

Initial commit: quant backtesting framework with daily trading simulator

2026-04-05 00:41:19 +08:00

agent_review.py

research: timestamped Yahoo analyst snapshots and a forward-only EPS-revision overlay

2026-10-12 05:16:19 -07:00

backtest_runner.py

fix(backtest): settle delisted US holdings (engine v3), PIT membership before 2011, registry causality test

2026-10-10 00:21:49 -07:00

bridge.py

live: commit the TrendRider V9/V10 registrations the monitor already runs

2026-10-09 22:20:28 -07:00

CLAUDE.md

research: auction audit of the overnight sleeve's prices (PASS: 0.2 bp a side)

2026-10-12 21:08:32 -07:00

data_manager.py

live: keep new sessions on subset refreshes; replay books from a backfilled day

2026-10-12 05:16:16 -07:00

execution.py

fix(backtest): settle delisted US holdings (engine v3), PIT membership before 2011, registry causality test

2026-10-10 00:21:49 -07:00

factor_attribution.py

Reject empty attribution semantics headers

2026-04-07 18:10:21 +08:00

main.py

fix(backtest): settle delisted US holdings (engine v3), PIT membership before 2011, registry causality test

2026-10-10 00:21:49 -07:00

Makefile

Add strategy ranking tool with Makefile shortcut

2026-05-14 12:49:14 +08:00

metrics.py

fix(report): correct periodic returns, injection metrics and live view

2026-09-25 01:16:33 +08:00

overnight_paper.py

overnight paper: count an order as sent only when Alpaca accepted it

2026-10-12 05:16:12 -07:00

precompute_backtest.py

fix: unify backtest execution and add forward validation candidates

2026-10-01 02:24:01 -07:00

pyproject.toml

feat: robust-momentum strategies live; fix live universe, lots and UI backtests

2026-09-25 19:12:02 +08:00

rank_strategies.py

Add strategy ranking tool with Makefile shortcut

2026-05-14 12:49:14 +08:00

README.md

auto mode for continuous running

2026-04-05 00:50:26 +08:00

signals.py

fix: unify backtest execution and add forward validation candidates

2026-10-01 02:24:01 -07:00

trader.py

live: record each session's target and its frictionless return; compare shows Ideal and Gap

2026-10-12 18:49:28 -07:00

universe_history.py

fix(backtest): settle delisted US holdings (engine v3), PIT membership before 2011, registry causality test

2026-10-10 00:21:49 -07:00

universe.py

feat: robust-momentum strategies live; fix live universe, lots and UI backtests

2026-09-25 19:12:02 +08:00

uv.lock

feat: robust-momentum strategies live; fix live universe, lots and UI backtests

2026-09-25 19:12:02 +08:00

weekly_strategy_report.py

Add weekly strategy report comparing top strategies to baselines

2026-05-14 12:49:18 +08:00

README.md

The file is empty.