Gahow Wang 81f4e3b32c research: factor census on the current panel; key the factor-rank cache to the panel ...

factor_census measures all 86 lab factors one way on the post-Tiingo PIT
S&P 500 panel (IC, quintile spread, top-20 alpha vs EW). One class A
(low_svr21, 2018+), two class B (accruals, rev_5), 69 N, no |t| >= 3.
Momentum and overnight_mom have no quintile spread; the house edge sits
in the top 10. --part construction compares the live construction.

rotation.factor_ranks reused ranks_us.pkl regardless of the panel. The
cache predated the Tiingo merge (643 of 787 columns), so callers silently
dropped the backfilled delisted names. The cache now carries a key file
(panel calendar, tickers, membership, factors.py hash) and is rebuilt
when it does not match.

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

2026-10-12 07:14:42 -07:00

..

__init__.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

activist_strategy.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

activists.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

alpha.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

analyst_estimates.py

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

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

attention.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

baselines.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

beat_qqq.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

concentration.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

construction.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

daytime_reversal.py

research: daytime reversal of the overnight gap on S&P 500 (STOP)

2026-10-09 22:07:26 -07:00

dip_buying.py

research: buy-the-dip studies, both STOP (kept as evidence)

2026-10-12 06:17:27 -07:00

dip_leverage_overlay.py

research: buy-the-dip studies, both STOP (kept as evidence)

2026-10-12 06:17:27 -07:00

diversifiers.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

earnings.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

engine.py

feat: US 3-sleeve portfolio and lowrisk_top20; US portfolio research harness

2026-09-29 01:03:50 +08:00

evaluate.py

fix: unify backtest execution and add forward validation candidates

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

export_curves.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

factor_census.py

research: factor census on the current panel; key the factor-rank cache to the panel

2026-10-12 07:14:42 -07:00

factor_scan.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

factors.py

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

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

fails.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_13d_targets.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_13d.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_13f.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_alpaca.py

research: 50%-target search — conservative book, daily quick checks, Alpaca intraday

2026-10-09 00:58:47 -07:00

fetch_cn_yahoo.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

fetch_cn.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

fetch_fails.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_gdelt.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_insider.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_lazy_prices.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

fetch_long_history.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

fetch_shortvolume.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_supply_links.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

fetch_tiingo.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

fetch_us_fundamentals.py

research: S&P 600 replication of mid-cap quality sleeves (all REJECT)

2026-10-08 18:46:45 -07:00

fetch_us_mid.py

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

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

fetch_us_sectors.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

fetch_us.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

fetch_wiki_attention.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

fund_eval.py

feat: US 3-sleeve portfolio and lowrisk_top20; US portfolio research harness

2026-09-29 01:03:50 +08:00

fundamentals.py

research: S&P 600 replication of mid-cap quality sleeves (all REJECT)

2026-10-08 18:46:45 -07:00

futures_trend.py

research: beta-hedged momentum (STOP) and 24-market futures TSMOM quick checks

2026-10-08 22:45:21 -07:00

hedged_momentum.py

research: beta-hedged momentum (STOP) and 24-market futures TSMOM quick checks

2026-10-08 22:45:21 -07:00

industry.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

insider_mid.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

insider.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

inst_flow.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

intraday_momentum.py

research: 50%-target search — conservative book, daily quick checks, Alpaca intraday

2026-10-09 00:58:47 -07:00

lazy_prices.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

lead_lag_small.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

lead_lag.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

letf_history.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

levered_book.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

managed_futures_book.py

research: 50%-target search — conservative book, daily quick checks, Alpaca intraday

2026-10-09 00:58:47 -07:00

midcap_sleeve.py

research: S&P 600 replication of mid-cap quality sleeves (all REJECT)

2026-10-08 18:46:45 -07:00

ml.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

momentum_fundamentals.py

chore: untrack generated data; add momentum + fundamentals experiment

2026-09-29 14:42:49 +08:00

news_volume.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

orb_stocks_in_play.py

research: ORB (STOP), overnight-only momentum (STOP), Alpaca paper forward test

2026-10-09 20:06:34 -07:00

overlays.py

feat: US 3-sleeve portfolio and lowrisk_top20; US portfolio research harness

2026-09-29 01:03:50 +08:00

overnight_book_mf.py

research: overnight-only momentum in the sleeve book (CONTINUE), CTA sleeve (KEEP)

2026-10-09 22:03:18 -07:00

overnight_book.py

research: overnight-only momentum in the sleeve book (CONTINUE), CTA sleeve (KEEP)

2026-10-09 22:03:18 -07:00

overnight_midsmall.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

overnight_only.py

research: ORB (STOP), overnight-only momentum (STOP), Alpaca paper forward test

2026-10-09 20:06:34 -07:00

panel_gaps.py

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

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

panel_mid.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

panel.py

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

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

persistence.py

feat: US 3-sleeve portfolio and lowrisk_top20; US portfolio research harness

2026-09-29 01:03:50 +08:00

qqq_scan.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

registered.py

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

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

report.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

review_live_us.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

rotation.py

research: factor census on the current panel; key the factor-rank cache to the panel

2026-10-12 07:14:42 -07:00

run_ml.py

research: point-in-time factor research harness (research/lab)

2026-09-25 19:11:59 +08:00

sector_cycle.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

short_horizon.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

short_vol.py

research: 50%-target search — conservative book, daily quick checks, Alpaca intraday

2026-10-09 00:58:47 -07:00

short_volume.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

small_cap_reversal.py

research: 50%-target search — conservative book, daily quick checks, Alpaca intraday

2026-10-09 00:58:47 -07:00

stepwise.py

fix: unify backtest execution and add forward validation candidates

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

stream_portfolio.py

research: risk-budgeted book of five return streams (REJECT)

2026-10-08 21:17:12 -07:00

theme_propagation.py

feat(research): supply-chain links, theme propagation, cycles, attention, small caps

2026-09-30 20:25:08 +08:00

tiingo_merge.py

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

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

trend_rider_long.py

feat: US 3-sleeve portfolio and lowrisk_top20; US portfolio research harness

2026-09-29 01:03:50 +08:00

trials.py

fix: unify backtest execution and add forward validation candidates

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

turn_of_month.py

research: 50%-target search — conservative book, daily quick checks, Alpaca intraday

2026-10-09 00:58:47 -07:00

union_shield.py

research: commit the 2026-10-07/08 studies left in the working tree, overnight mid/small (STOP)

2026-10-09 22:20:43 -07:00

universe_midcap.py

research: S&P 500 ∪ S&P 400 universe for overnight_recovery_top10 (FAIL)

2026-10-08 08:43:50 -07:00

us_final.py

fix: unify backtest execution and add forward validation candidates

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

us_sweep.py

fix: unify backtest execution and add forward validation candidates

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

us_target50.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00

vol_trend.py

feat: us_momentum_qqq_trend; alpha-vs-QQQ research across new data sources

2026-09-29 13:40:15 +08:00