dennisthiessen/signal-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

research: sector residual, earnings gap/SUE, history-depth scaffolding

Browse Source 
Tier-1 alpha research (local only, no production deploy):

Sector residual momentum: two-factor SPY+sector residual and sector demean signals, IC harness + A/B. Sector resid clears pre-registered bars narrowly (PROMOTE for human wire design only). Sector demean fails t vs market resid.

Earnings: earnings_events backfill (FMP bulk paid; FMP/AV per-symbol), 2a gap diagnostic report-only, 2b SUE IC (PARK; incomplete 48/506 coverage).

History-depth: pre-registered doc + runner for MacBook deep rebuild/harness.

Do not ship production residual or filters from this branch.
This commit is contained in:
dennisthiessen
2026-07-19 09:33:34 +02:00
parent 8f285acb00
commit fa25b6ee68
18 changed files with 6093 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/earnings-backfill-status.json
+15
View File
@@ -0,0 +1,15 @@
{
"mode": "per_symbol",
"fmp_requests": 25,
"events_written_this_run": 2541,
"total_events": 5612,
"symbols_done": 48,
"symbols_universe": 506,
"announce_date_range": {
"min": "1985-08-31",
"max": "2026-07-16"
},
"events_with_actual_and_estimate": 5018,
"budget": 25,
"complete": false
}
reports/earnings-gap-sue-20260719-093129.json
+331
View File
@@ -0,0 +1,331 @@
{
"generated_at": "2026-07-19T09:31:29.078611",
"data_provenance": {
"snapshot": "C:\\Workspace\\signal-platform\\backtest_snapshots\\prod.sqlite",
"n_earnings_events": 5612,
"backfill_meta": {
"done": 48,
"universe_tickers": 506
},
"announce_range": {
"min": "1985-08-31",
"max": "2026-07-16"
},
"with_actual_and_estimate": 5018
},
"experiment_2a": {
"sim_summary": {
"sharpe": 2.09,
"sharpe_se": 0.497,
"cagr_pct": 51.6,
"max_drawdown_pct": 21.4,
"trades": 322,
"total_return_pct": 424.6
},
"n_trades_parsed": 322,
"q1_losses_worse_than_minus_1r": {
"n_losses_lt_minus_1r": 28,
"n_with_earnings_in_hold": 1,
"fraction_with_earnings": 0.0357,
"all_trades_with_earnings_in_hold": 14,
"fraction_all_trades_with_earnings": 0.0435
},
"q2_entry_within_3d_before_announce": {
"pre_earn_entries": {
"n": 4,
"mean": 1.9379,
"win_rate": 0.5,
"p05": -1.2428,
"p25": -0.8833,
"p50": 1.1209,
"p75": 3.942,
"p95": 6.2623,
"min": -1.3327,
"max": 6.8424
},
"other_entries": {
"n": 318,
"mean": 0.6965,
"win_rate": 0.3711,
"p05": -1.1052,
"p25": -1.0,
"p50": -0.8259,
"p75": 2.1053,
"p95": 6.077,
"min": -3.2587,
"max": 12.8654
},
"all_entries": {
"n": 322,
"mean": 0.7119,
"win_rate": 0.3727,
"p05": -1.1209,
"p25": -1.0,
"p50": -0.8251,
"p75": 2.1595,
"p95": 6.2246,
"min": -3.2587,
"max": 12.8654
},
"tail_trim_note": "Compare p95/max and mean of pre_earn vs other. Rising win_rate with falling mean/p95 = right-tail trim red flag."
},
"note": "REPORT-ONLY \u2014 no filter shipped."
},
"experiment_2b": {
"signal_eval_side_by_side": {
"mom_12_1": {
"signal": "mom_12_1",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0531,
"ic_t_stat": 1.61,
"ic_positive_pct": 65.7,
"mean_quintile_spread": 0.0206,
"reliable": true
},
"mom_12_1_resid": {
"signal": "mom_12_1_resid",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0552,
"ic_t_stat": 1.98,
"ic_positive_pct": 60.0,
"mean_quintile_spread": 0.0207,
"reliable": true
},
"mom_12_1_sector_resid": {
"signal": "mom_12_1_sector_resid",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0578,
"ic_t_stat": 2.34,
"ic_positive_pct": 65.7,
"mean_quintile_spread": 0.0245,
"reliable": true
},
"mom_12_1_sector_demeaned": {
"signal": "mom_12_1_sector_demeaned",
"weeks": 35,
"avg_cross_section": 496.7,
"mean_ic": 0.034,
"ic_t_stat": 1.32,
"ic_positive_pct": 62.9,
"mean_quintile_spread": 0.0154,
"reliable": true
},
"sue_latest": {
"signal": "sue_latest",
"weeks": 44,
"avg_cross_section": 47.4,
"mean_ic": 0.0172,
"ic_t_stat": 0.6,
"ic_positive_pct": 47.7,
"mean_quintile_spread": 0.0064,
"reliable": true
},
"fip_id": {
"signal": "fip_id",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": -0.045,
"ic_t_stat": -2.91,
"ic_positive_pct": 25.7,
"mean_quintile_spread": -0.0168,
"reliable": true
}
},
"signal_eval_identical_sue_subset": {
"mom_12_1": {
"signal": "mom_12_1",
"weeks": 35,
"avg_cross_section": 47.3,
"mean_ic": -0.0174,
"ic_t_stat": -0.42,
"ic_positive_pct": 45.7,
"mean_quintile_spread": 0.0077,
"reliable": true
},
"mom_12_1_resid": {
"signal": "mom_12_1_resid",
"weeks": 35,
"avg_cross_section": 47.3,
"mean_ic": -0.0104,
"ic_t_stat": -0.27,
"ic_positive_pct": 51.4,
"mean_quintile_spread": 0.0075,
"reliable": true
},
"sue_latest": {
"signal": "sue_latest",
"weeks": 44,
"avg_cross_section": 47.4,
"mean_ic": 0.0172,
"ic_t_stat": 0.6,
"ic_positive_pct": 47.7,
"mean_quintile_spread": 0.0064,
"reliable": true
}
},
"identical_subset_note": "Mom baselines re-scored only on (week, symbol) cells where SUE exists. Use this table when backfill is incomplete \u2014 full-universe mom N is not comparable.",
"full_signal_eval": [
{
"signal": "vol_6m",
"weeks": 39,
"avg_cross_section": 498.2,
"mean_ic": 0.0609,
"ic_t_stat": 1.48,
"ic_positive_pct": 64.1,
"mean_quintile_spread": 0.0337,
"reliable": true
},
{
"signal": "mom_12_1_sector_resid",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0578,
"ic_t_stat": 2.34,
"ic_positive_pct": 65.7,
"mean_quintile_spread": 0.0245,
"reliable": true
},
{
"signal": "mom_12_1_resid",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0552,
"ic_t_stat": 1.98,
"ic_positive_pct": 60.0,
"mean_quintile_spread": 0.0207,
"reliable": true
},
{
"signal": "mom_12_1",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0531,
"ic_t_stat": 1.61,
"ic_positive_pct": 65.7,
"mean_quintile_spread": 0.0206,
"reliable": true
},
{
"signal": "mom_12_1_sector_demeaned",
"weeks": 35,
"avg_cross_section": 496.7,
"mean_ic": 0.034,
"ic_t_stat": 1.32,
"ic_positive_pct": 62.9,
"mean_quintile_spread": 0.0154,
"reliable": true
},
{
"signal": "sue_latest",
"weeks": 44,
"avg_cross_section": 47.4,
"mean_ic": 0.0172,
"ic_t_stat": 0.6,
"ic_positive_pct": 47.7,
"mean_quintile_spread": 0.0064,
"reliable": true
},
{
"signal": "trend_200",
"weeks": 37,
"avg_cross_section": 497.9,
"mean_ic": 0.0161,
"ic_t_stat": 0.44,
"ic_positive_pct": 59.5,
"mean_quintile_spread": 0.006,
"reliable": true
},
{
"signal": "reversal_1m",
"weeks": 43,
"avg_cross_section": 498.7,
"mean_ic": 0.0059,
"ic_t_stat": 0.22,
"ic_positive_pct": 53.5,
"mean_quintile_spread": 0.0053,
"reliable": true
},
{
"signal": "mom_6_1",
"weeks": 39,
"avg_cross_section": 498.2,
"mean_ic": 0.0051,
"ic_t_stat": 0.21,
"ic_positive_pct": 56.4,
"mean_quintile_spread": 0.0087,
"reliable": true
},
{
"signal": "mom_3_1",
"weeks": 42,
"avg_cross_section": 498.5,
"mean_ic": -0.0064,
"ic_t_stat": -0.25,
"ic_positive_pct": 50.0,
"mean_quintile_spread": 0.0046,
"reliable": true
},
{
"signal": "high_52w",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": -0.0086,
"ic_t_stat": -0.26,
"ic_positive_pct": 54.3,
"mean_quintile_spread": -0.0088,
"reliable": true
},
{
"signal": "fip_id",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": -0.045,
"ic_t_stat": -2.91,
"ic_positive_pct": 25.7,
"mean_quintile_spread": -0.0168,
"reliable": true
}
],
"sue_grade": {
"green": false,
"checks": {
"mean_ic": 0.0172,
"sign_positive": true,
"abs_ge_0_03": false,
"reliable": true,
"ic_t_stat": 0.6,
"weeks": 44
},
"reason": "iron rule not met",
"row": {
"signal": "sue_latest",
"weeks": 44,
"avg_cross_section": 47.4,
"mean_ic": 0.0172,
"ic_t_stat": 0.6,
"ic_positive_pct": 47.7,
"mean_quintile_spread": 0.0064,
"reliable": true
}
},
"momentum_conditional_sue": {
"mean_ic": -0.0065,
"ic_t_stat": -0.1,
"weeks": 35,
"note": "IC of sue_latest within top mom_12_1 quintile (non-overlapping weeks)"
},
"sue_coverage": {
"symbols_with_sue": 48,
"avg_weeks_with_sue": 47.1,
"weeks_with_min_cross_section": 256
}
},
"verdict": "PARK",
"verdict_detail": "SUE IC=0.0172 below iron bar or unreliable; keep data, no wire.",
"human_next": "- No SUE book change.\n- Read 2a tails before considering any earnings-avoid filter.",
"report_path": "reports/earnings-gap-sue-20260719-093129.json",
"fmp_note": "Bulk earnings-calendar is paid (402 on free tier). Backfill used per-symbol /stable/earnings; see earnings-backfill-status.json."
}
reports/earnings-gap-sue-20260719-093129.md
+202
View File
@@ -0,0 +1,202 @@
# Earnings gap diagnostic + SUE / PEAD (Tier-1 alpha research)
**Status:** **PARK** (incomplete earnings coverage; SUE fails iron rule on available sample).
**Branch:** `research/earnings-gap-and-sue`
**Production impact:** none. Local research only. **No filters shipped from 2a.**
**Artifacts:** `reports/earnings-gap-sue-20260719-093129.json` (+ companion `.md`)
---
## Pre-registration (locked before first research run)
### Data
- Historical earnings calendar for the production universe over the full snapshot
window (and deeper if the feed provides it).
- Preferred source: FMP **date-range earnings-calendar** (bulk). If unavailable on
free tier, fall back to per-symbol `/stable/earnings` with request accounting.
- Store in a real local table `earnings_events` (symbol + announce_date key).
- Point-in-time: a surprise is usable only from **announce date + 1 trading day**
onward.
### Experiment 2a — earnings-gap risk (defense, report-only)
Join simulated production-config trades (`fill_mode=close`) with earnings dates.
**Pre-registered questions:**
1. What fraction of losses worse than **−1R** occur with an earnings announcement
**between entry and exit** (inclusive of the holding window)?
2. What is the mean R of entries taken within **3 trading days BEFORE** an
announcement vs all other entries — report **both tails** of the R
distribution (rule 4: any earnings-avoid entry filter is presumed guilty of
right-tail trimming until the win distribution shows otherwise)?
**Output:** distributions and counts only.
**No filter is shipped.** If numbers argue for a filter → report and stop.
### Experiment 2b — SUE / PEAD (offense)
Signal `sue_latest`:
\[
\text{SUE} = \frac{\text{actual} - \text{estimate}}{\sigma(\text{trailing 8 surprises})}
\]
Fallback if estimate history is thin: scale surprise by price.
Carry forward from announce+1 for **63 trading days**, else NaN (name drops out
of that cross-section).
**Iron rule (IC harness):** mean weekly Spearman IC on non-overlapping weeks;
\|mean IC\| ≥ ~0.03, **positive** sign (drift), `reliable: true` (≥12 windows).
Always side-by-side with `mom_12_1` and `mom_12_1_resid` on **identical**
cross-sections.
Also report **momentum-conditional** IC (within top momentum quintile).
**If it passes iron rule:** STOP and report. Book-integration design is a
separate human-approved step — do not wire.
### Verdict labels
| label | meaning |
|---|---|
| **PROMOTE** | (2b only) iron rule cleared → human designs tilt/gate |
| **PARK** | Interesting but incomplete / weak |
| **DEAD** | No edge / diagnostic argues against action |
| **REPORT-ONLY** | (2a) always — never auto-filter |
---
## Data provenance
| item | result |
|---|---|
| Snapshot | `backtest_snapshots/prod.sqlite` (506 names) |
| FMP bulk `earnings-calendar` | **402 Premium** — not available on free tier |
| FMP per-symbol `/stable/earnings` | used; hit daily rate limit ~225 reqs |
| Alpha Vantage `EARNINGS` | used for +24 symbols (announce = `reportedDate`) |
| Symbols with events | **48 / 506 (9.5%)** |
| Total events | 5,612 (5,018 with actual+estimate) |
| Announce range | 1985-08-31 → 2026-07-16 |
| FMP requests (first day) | 260 FMP + 25 AV (see `reports/earnings-backfill-status.json`) |
**Incomplete backfill is first-class.** 2a under-detects earnings overlaps; 2b SUE
cross-section averages **~47 names**, not ~500. Resume:
```bash
# Day N (FMP free ~250/day; AV free ~25/day — prefer FMP after reset)
python scripts/backfill_earnings_events.py \
--snapshot backtest_snapshots/prod.sqlite \
--provider fmp --force-symbol --limit 250 --sleep 0.4
# When done==506:
python scripts/run_earnings_research.py \
--snapshot backtest_snapshots/prod.sqlite \
--workers 6 --allow-spawn
```
---
## Results
Generated: `2026-07-19T09:31:29`
### 2a — Earnings-gap risk (report-only)
Production book sim: Sharpe 2.09 (SE 0.497), CAGR 51.6%, max DD 21.4%, **322 trades**,
`fill_mode=close`.
#### Q1 — Losses worse than −1R with earnings in hold
| metric | value |
|---|---:|
| n losses < −1R | 28 |
| of which earnings in hold | **1** |
| fraction | **3.6%** |
| all trades with earnings in hold | 14 / 322 (4.4%) |
**Read:** On incomplete earnings labels this is a **lower bound** on earnings
overlap, not a clean “earnings rarely hurt.” Do **not** conclude earnings risk is
immaterial until coverage ≥ ~95% of the book’s names.
#### Q2 — Entry within 3 trading days before announce (both tails)
| cohort | n | mean R | win rate | p05 | p50 | p95 | max |
|---|---:|---:|---:|---:|---:|---:|---:|
| pre-earn (≤3d before) | **4** | 1.94 | 50% | −1.24 | 1.12 | 6.26 | 6.84 |
| other | 318 | 0.70 | 37% | −1.11 | −0.83 | 6.08 | **12.87** |
| all | 322 | 0.71 | 37% | −1.12 | −0.83 | 6.22 | 12.87 |
**Tail-trim presumption:** n=4 is not a sample. Point estimate does **not** show
right-tail destruction of pre-earn entries (p95 similar; max actually higher in
“other”). **No earnings-avoid filter is supported.** Re-run after full backfill.
---
### 2b — SUE / PEAD IC
#### Full-universe harness (mom on ~500; SUE only where labeled)
| signal | mean_ic | ic_t_stat | weeks | avg_N | reliable |
|---|---:|---:|---:|---:|---|
| mom_12_1_sector_resid | 0.0578 | 2.34 | 35 | 497.7 | true |
| mom_12_1_resid | 0.0552 | 1.98 | 35 | 497.7 | true |
| mom_12_1 | 0.0531 | 1.61 | 35 | 497.7 | true |
| **sue_latest** | **0.0172** | **0.6** | 44 | **47.4** | true |
| fip_id | −0.045 | −2.91 | 35 | 497.7 | true |
#### Identical SUE subset (fair side-by-side — use this while coverage is thin)
| signal | mean_ic | ic_t_stat | weeks | avg_N |
|---|---:|---:|---:|---:|
| sue_latest | 0.0172 | 0.6 | 44 | 47.4 |
| mom_12_1 | −0.0174 | −0.42 | 35 | 47.3 |
| mom_12_1_resid | −0.0104 | −0.27 | 35 | 47.3 |
On the thin labeled subset, momentum itself is noise — so the subset is not yet
a meaningful PEAD test.
#### Momentum-conditional SUE (top mom quintile)
| metric | value |
|---|---:|
| mean IC | **−0.0065** |
| t | −0.1 |
| weeks | 35 |
Wrong sign vs “ride positive surprises inside the momentum gate.”
**Iron rule:** fail (\|IC\| 0.017 < 0.03; t 0.6). **No promote.**
---
## Verdict
| piece | verdict |
|---|---|
| **2a earnings-gap** | **REPORT-ONLY** — no filter. Coverage too thin for risk claims; tails do not argue for an avoid-filter on n=4. |
| **2b SUE** | **PARK** (effectively not green). Mild positive IC on ~48 names; fails iron bar; mom-conditional flat/negative. Re-score after full backfill before DEAD. |
| **Production** | **no change** |
---
## What a human must decide next
1. Resume multi-day earnings backfill to **506/506**, then re-run
`run_earnings_research.py` (heavy — MacBook OK).
2. Do **not** ship an earnings-avoid entry filter from 2a.
3. Do **not** wire SUE until a full-coverage IC clears the iron rule (and
preferably mom-conditional > 0).
4. Do not merge into main strategy docs without review.
---
## Implementation notes
| piece | role |
|---|---|
| `scripts/backfill_earnings_events.py` | bulk attempt → FMP/AV per-symbol; `earnings_events` + meta on snapshot |
| `scripts/run_earnings_research.py` | 2a trade join + 2b SUE IC / mom-conditional |
| Snapshot table `earnings_events` | real table (not SystemSetting JSON) |
reports/sector-residual-20260719-083356.json
+412
View File
@@ -0,0 +1,412 @@
{
"generated_at": "2026-07-19T08:33:56.651229",
"snapshot_guard": {
"snapshot": "C:\\Workspace\\signal-platform\\backtest_snapshots\\prod.sqlite",
"manifest": null,
"manifest_ok": null,
"note": "No completion manifest (prod.sqlite is expected without one). Bar-count sanity still applied.",
"ticker_count": 506,
"ohlcv_row_count": 629263,
"bars_min_avg_max": {
"min": 14,
"avg": 1246.1,
"max": 1261
},
"ohlcv_date_range": {
"min": "2021-06-24",
"max": "2026-07-02"
},
"benchmark_prices": [
{
"symbol": "SPY",
"n": 1516,
"min": "2020-07-06",
"max": "2026-07-17"
},
{
"symbol": "XLB",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLC",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLE",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLF",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLI",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLK",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLP",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLRE",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLU",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLV",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
},
{
"symbol": "XLY",
"n": 1512,
"min": "2020-07-10",
"max": "2026-07-17"
}
],
"missing_sector_etfs": []
},
"sector_coverage": {
"universe": 506,
"mapped": 505,
"mapped_pct": 99.8,
"with_etf": 505,
"missing": [
"RHM"
],
"by_sector": {
"Industrials": 81,
"Financials": 75,
"Information Technology": 72,
"Health Care": 58,
"Consumer Discretionary": 47,
"Consumer Staples": 34,
"Real Estate": 31,
"Utilities": 31,
"Materials": 26,
"Communication Services": 23,
"Energy": 22,
"Consumer Defensive": 2,
"Technology": 2,
"Financial Services": 1
}
},
"sector_map_path": "C:\\Workspace\\signal-platform\\data\\research\\ticker_sector_map.json",
"signal_eval": [
{
"signal": "vol_6m",
"weeks": 39,
"avg_cross_section": 498.2,
"mean_ic": 0.0609,
"ic_t_stat": 1.48,
"ic_positive_pct": 64.1,
"mean_quintile_spread": 0.0337,
"reliable": true
},
{
"signal": "mom_12_1_sector_resid",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0578,
"ic_t_stat": 2.34,
"ic_positive_pct": 65.7,
"mean_quintile_spread": 0.0245,
"reliable": true
},
{
"signal": "mom_12_1_resid",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0552,
"ic_t_stat": 1.98,
"ic_positive_pct": 60.0,
"mean_quintile_spread": 0.0207,
"reliable": true
},
{
"signal": "mom_12_1",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0531,
"ic_t_stat": 1.61,
"ic_positive_pct": 65.7,
"mean_quintile_spread": 0.0206,
"reliable": true
},
{
"signal": "mom_12_1_sector_demeaned",
"weeks": 35,
"avg_cross_section": 496.7,
"mean_ic": 0.034,
"ic_t_stat": 1.32,
"ic_positive_pct": 62.9,
"mean_quintile_spread": 0.0154,
"reliable": true
},
{
"signal": "trend_200",
"weeks": 37,
"avg_cross_section": 497.9,
"mean_ic": 0.0161,
"ic_t_stat": 0.44,
"ic_positive_pct": 59.5,
"mean_quintile_spread": 0.006,
"reliable": true
},
{
"signal": "reversal_1m",
"weeks": 43,
"avg_cross_section": 498.7,
"mean_ic": 0.0059,
"ic_t_stat": 0.22,
"ic_positive_pct": 53.5,
"mean_quintile_spread": 0.0053,
"reliable": true
},
{
"signal": "mom_6_1",
"weeks": 39,
"avg_cross_section": 498.2,
"mean_ic": 0.0051,
"ic_t_stat": 0.21,
"ic_positive_pct": 56.4,
"mean_quintile_spread": 0.0087,
"reliable": true
},
{
"signal": "mom_3_1",
"weeks": 42,
"avg_cross_section": 498.5,
"mean_ic": -0.0064,
"ic_t_stat": -0.25,
"ic_positive_pct": 50.0,
"mean_quintile_spread": 0.0046,
"reliable": true
},
{
"signal": "high_52w",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": -0.0086,
"ic_t_stat": -0.26,
"ic_positive_pct": 54.3,
"mean_quintile_spread": -0.0088,
"reliable": true
},
{
"signal": "fip_id",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": -0.045,
"ic_t_stat": -2.91,
"ic_positive_pct": 25.7,
"mean_quintile_spread": -0.0168,
"reliable": true
}
],
"ic_grades": {
"mom_12_1_sector_resid": {
"promote_to_ab": true,
"checks": {
"sign_ok": true,
"abs_mean_ic_ge_0_03": true,
"reliable": true,
"t_ge_resid": true,
"mean_ic": 0.0578,
"ic_t_stat": 2.34,
"resid_ic_t_stat": 1.98,
"weeks": 35
},
"reason": "clears iron rule and t \u2265 mom_12_1_resid \u2014 authorized for A/B only",
"row": {
"signal": "mom_12_1_sector_resid",
"weeks": 35,
"avg_cross_section": 497.7,
"mean_ic": 0.0578,
"ic_t_stat": 2.34,
"ic_positive_pct": 65.7,
"mean_quintile_spread": 0.0245,
"reliable": true
}
},
"mom_12_1_sector_demeaned": {
"promote_to_ab": false,
"checks": {
"sign_ok": true,
"abs_mean_ic_ge_0_03": true,
"reliable": true,
"t_ge_resid": false,
"mean_ic": 0.034,
"ic_t_stat": 1.32,
"resid_ic_t_stat": 1.98,
"weeks": 35
},
"reason": "does not clear pre-registered IC promotion bar",
"row": {
"signal": "mom_12_1_sector_demeaned",
"weeks": 35,
"avg_cross_section": 496.7,
"mean_ic": 0.034,
"ic_t_stat": 1.32,
"ic_positive_pct": 62.9,
"mean_quintile_spread": 0.0154,
"reliable": true
}
}
},
"portfolio_ab": {
"signal": "mom_12_1_sector_resid",
"ranking_key": "residual_high_vol_blend_80_20_score",
"fill_mode": "close",
"validation_split": "2024-07-01",
"control": {
"label": "control_mom_12_1_resid",
"n_qualified_longs": 1086,
"windows": {
"train": {
"sharpe": 1.3,
"sharpe_se": 0.685,
"cagr_pct": 29.2,
"max_drawdown_pct": 21.4,
"total_return_pct": 70.9,
"trades": 176,
"win_rate_pct": null,
"avg_r": null,
"n_returns": 525,
"return_skew": 0.3722,
"return_kurtosis": 4.6208,
"psr": 0.971
},
"validation": {
"sharpe": 2.92,
"sharpe_se": 0.709,
"cagr_pct": 76.3,
"max_drawdown_pct": 11.7,
"total_return_pct": 210.7,
"trades": 150,
"win_rate_pct": null,
"avg_r": null,
"n_returns": 501,
"return_skew": 0.1734,
"return_kurtosis": 4.4625,
"psr": 1.0
},
"full": {
"sharpe": 2.09,
"sharpe_se": 0.497,
"cagr_pct": 51.6,
"max_drawdown_pct": 21.4,
"total_return_pct": 424.6,
"trades": 322,
"win_rate_pct": null,
"avg_r": null,
"n_returns": 1000,
"return_skew": 0.2686,
"return_kurtosis": 4.5653,
"psr": 1.0
}
}
},
"treatment": {
"label": "treatment_mom_12_1_sector_resid",
"n_qualified_longs": 1210,
"windows": {
"train": {
"sharpe": 1.57,
"sharpe_se": 0.677,
"cagr_pct": 35.5,
"max_drawdown_pct": 19.8,
"total_return_pct": 90.0,
"trades": 176,
"win_rate_pct": null,
"avg_r": null,
"n_returns": 530,
"return_skew": 0.466,
"return_kurtosis": 4.4413,
"psr": 0.99
},
"validation": {
"sharpe": 2.57,
"sharpe_se": 0.701,
"cagr_pct": 66.3,
"max_drawdown_pct": 14.8,
"total_return_pct": 176.4,
"trades": 163,
"win_rate_pct": null,
"avg_r": null,
"n_returns": 501,
"return_skew": 0.3003,
"return_kurtosis": 4.4305,
"psr": 0.9999
},
"full": {
"sharpe": 2.09,
"sharpe_se": 0.491,
"cagr_pct": 51.0,
"max_drawdown_pct": 19.8,
"total_return_pct": 421.3,
"trades": 337,
"win_rate_pct": null,
"avg_r": null,
"n_returns": 1005,
"return_skew": 0.4066,
"return_kurtosis": 4.3627,
"psr": 1.0
}
}
},
"promotion": {
"promote": true,
"checks": {
"validation_sharpe_ge_control_minus_half_se": true,
"full_sharpe_not_worse": true,
"full_maxdd_not_worse": true,
"control_validation_sharpe": 2.92,
"treatment_validation_sharpe": 2.57,
"se_used": 0.701,
"control_full_sharpe": 2.09,
"treatment_full_sharpe": 2.09,
"control_full_maxdd": 21.4,
"treatment_full_maxdd": 19.8
},
"reason": "clears pre-registered A/B bar \u2014 human decides wire-in"
}
},
"verdict": "PROMOTE",
"verdict_detail": "mom_12_1_sector_resid cleared IC + A/B bars. Human must design wire-in; do not ship from this branch.",
"human_next": "- Approve or reject production residual swap vs dual-signal design.\n- If sector-cap arm ran, review tail-trim diagnostics before any cap.",
"report_path": "reports/sector-residual-20260719-083356.json",
"pre_registration": {
"iron_ic_bar": 0.03,
"validation_split": "2024-07-01",
"fill_mode": "close",
"cost_per_side": 0.001,
"ab_rule": "val Sharpe >= control - 0.5*SE; full Sharpe & maxDD not worse"
}
}
reports/sector-residual-20260719-083356.md
+237
View File
@@ -0,0 +1,237 @@
# Sector-residual momentum (Tier-1 alpha research)
**Status:** **PROMOTE (to human design decision only)** — IC + A/B bars cleared; **do not ship**.
**Branch:** `research/sector-residual-momentum`
**Production impact:** none. Local research only. No scheduler / gate / prod-config changes.
**Artifacts:** `reports/sector-residual-20260719-083356.json` (+ companion `.md`)
---
## Pre-registration (locked before first research run)
### Hypothesis
Residualizing 12–1 momentum against the sector, not only the market, reduces
factor volatility at similar return (Blitz / Huij / Martens-style) → higher
Sharpe on the production book when the residual replaces market-only residual
as the momentum leg.
### Signals (candidates)
| signal | construction |
|---|---|
| `mom_12_1_sector_resid` | Two-factor residual vs SPY + ticker’s sector ETF. Same window as `mom_12_1_resid`: ≥100 daily obs, 252-bar lookback, 21-bar skip; two-factor OLS betas **without intercept**; cumulate residual returns over the formation window. |
| `mom_12_1_sector_demeaned` | Plain `mom_12_1` minus the **cross-sectional** mean of `mom_12_1` within the same GICS sector that week (≥2 names in sector). No regression. |
### Baselines (same run, same cross-sections — iron rule)
Always report side-by-side with:
- `mom_12_1`
- `mom_12_1_resid`
Computed on the **identical** weekly non-overlapping cross-sections in this run.
Never compare against IC numbers from another report.
### Iron rule (IC harness)
Source of truth: `_signal_evaluation` in `app/services/backtest_service.py`.
- Mean weekly Spearman IC on **non-overlapping** weekly windows
- Bar: \|mean IC\| ≥ ~0.03, **consistent positive sign**, `reliable: true` (≥ 12 windows)
### Promotion to portfolio A/B (candidate → book)
A candidate promotes to A/B **only if**:
1. It clears the iron-rule bar **and**
2. Its IC **t-stat ≥** that of `mom_12_1_resid` on the same cross-sections.
### Portfolio A/B grading (if and only if IC promotion fires)
- Swap candidate in as the **momentum leg** of the production 80/20 momentum/vol
rank **and** as the gate-percentile signal.
- `fill_mode=close`, `COST_PER_SIDE = 0.001`, full config otherwise unchanged.
- Validation window = entries ≥ **2024-07-01** (call it **validation**, not
holdout — contaminated by prior experiments).
- Pre-registered promotion bar:
- validation Sharpe ≥ control − 0.5·SE
- full-period Sharpe and max-DD **not worse** than control
- Report Lo / Mertens-adjusted SEs.
### Optional sector-cap sub-experiment
Only if labels are in **and** A/B ran: max **3** positions per sector in the
10-slot book. Same A/B grading. **Tail-trim presumption of guilt** (rule 4):
report entry counts and both tails of the R distribution. Rising win rate with
falling Sharpe/CAGR = red flag → do not promote.
**This run:** sector-cap arm **not executed** (optional; A/B unconstrained book
only). Can be a human-approved follow-up.
### Verdict labels
| label | meaning |
|---|---|
| **PROMOTE** | Clears pre-registered bar; human decides next (wire design separate) |
| **PARK** | Inconclusive / weak; keep machinery, no book change |
| **DEAD** | Failed iron rule or worse than residual baseline with clear sign |
### Explicit non-goals
- No production deploy from this doc
- Do not resurrect: take-profit exits, EV gate, regime entry-blocking,
inverse-vol sizing, gap-caps, unconditional FIP filter
---
## Data provenance
### Snapshot race guard
| check | result |
|---|---|
| Snapshot path | `backtest_snapshots/prod.sqlite` |
| Manifest | none (expected for prod snapshot); bar-count sanity applied |
| Tickers / OHLCV | **506** / **629,263** |
| Bars min / avg / max | 14 / 1246.1 / 1261 |
| OHLCV range | 2021-06-24 → 2026-07-02 |
| Partial-build red flags | none (avg bars healthy) |
Integrity fingerprint on same run: `fip_id` mean IC **−0.045** / t **−2.91**
(35 weeks, N≈498) — matches the established prod fingerprint.
### Sector labels
| source | count |
|---|---:|
| Public S&P 500 GICS CSV | 496 newly filled |
| FMP profile requests | 10 (all missing after CSV) |
| Mapped / universe | **505 / 506 (99.8%)** |
| With mappable ETF | 505 |
| Still missing | **RHM** only |
Persist path: `data/research/ticker_sector_map.json`.
FMP aliases (`Technology`, `Consumer Defensive`, `Financial Services`) map to
SPDRs via the alias table in `app/services/sector_map.py`.
### Sector ETFs in `benchmark_prices` (auxiliary only — not tradable)
| symbol | bars | min date | max date |
|---|---:|---|---|
| SPY | 1516 | 2020-07-06 | 2026-07-17 |
| XLB…XLY (11) | 1512 each | 2020-07-10 | 2026-07-17 |
Fetched via Alpaca `Adjustment.SPLIT` into **`benchmark_prices`** (same table as
SPY) so they never enter the ticker universe or candidate replay.
---
## Results
Generated: `2026-07-19T08:33:56`
### IC harness (identical cross-sections, production 506-name universe)
| signal | mean_ic | ic_t_stat | weeks | avg_N | reliable | ic+_pct | quintile spread |
|---|---:|---:|---:|---:|---|---:|---:|
| **mom_12_1_sector_resid** | **0.0578** | **2.34** | 35 | 497.7 | true | 65.7 | 0.0245 |
| mom_12_1_resid | 0.0552 | 1.98 | 35 | 497.7 | true | 60.0 | 0.0207 |
| mom_12_1 | 0.0531 | 1.61 | 35 | 497.7 | true | 65.7 | 0.0206 |
| mom_12_1_sector_demeaned | 0.0340 | 1.32 | 35 | 496.7 | true | 62.9 | 0.0154 |
### IC promotion grades
| candidate | iron rule | t ≥ resid | promote_to_ab |
|---|---|---|---|
| `mom_12_1_sector_resid` | pass (IC 0.058, +sign, reliable) | **yes** (2.34 ≥ 1.98) | **yes** |
| `mom_12_1_sector_demeaned` | pass (IC 0.034, +sign, reliable) | **no** (1.32 < 1.98) | **no** |
### Portfolio A/B — `mom_12_1_sector_resid` as residual leg
Config: production 80/20 residual/high-vol rank + gate percentile, `fill_mode=close`,
cost 10 bps/side, ATR trail / gate-reset re-entry as live. Validation split
2024-07-01.
| window | arm | Sharpe | Sharpe SE (Mertens) | CAGR % | max DD % | trades | n_days |
|---|---|---:|---:|---:|---:|---:|---:|
| train | control (resid) | 1.30 | 0.685 | 29.2 | 21.4 | 176 | 525 |
| train | treatment (sector resid) | **1.57** | 0.677 | **35.5** | **19.8** | 176 | 530 |
| validation | control | **2.92** | 0.709 | **76.3** | **11.7** | 150 | 501 |
| validation | treatment | 2.57 | 0.701 | 66.3 | 14.8 | 163 | 501 |
| full | control | 2.09 | 0.497 | 51.6 | 21.4 | 322 | 1000 |
| full | treatment | 2.09 | 0.491 | 51.0 | **19.8** | 337 | 1005 |
**Pre-registered A/B checks**
| check | result |
|---|---|
| val Sharpe ≥ control − 0.5·SE | **pass** (2.57 ≥ 2.92 − 0.5×0.701 = 2.5695) — **knife-edge** |
| full Sharpe not worse | **pass** (2.09 = 2.09) |
| full max DD not worse | **pass** (19.8 < 21.4) |
Qualified long candidates: control 1086 vs treatment 1210 (sector residual
gates a slightly larger set).
---
## Verdict
| signal | verdict | note |
|---|---|---|
| **`mom_12_1_sector_resid`** | **PROMOTE → human wire-in decision** | IC modestly beats market residual; A/B clears pre-reg bar narrowly. **Do not ship from this branch.** |
| **`mom_12_1_sector_demeaned`** | **DEAD** (for promotion) | Iron-rule IC magnitude ok, but t-stat loses to `mom_12_1_resid`. Cheap variant not competitive. |
### Read carefully (for the human)
1. **IC edge is real but small.** Sector residual IC 0.0578 / t 2.34 vs market
residual 0.0552 / t 1.98 on the **same** 35 windows — better consistency
(ic+ 65.7% vs 60%) and slightly higher mean, not a different factor class.
2. **A/B is not a clear Sharpe win.** Full-period Sharpe is flat (2.09).
Validation Sharpe is **lower** than control (2.57 vs 2.92) and only clears
the pre-registered “within 0.5 SE” cushion by ~0.001. Train improves;
validation worsens — classic regime-split noise on ~2 years.
3. **Risk side is friendly.** Full max DD improves (19.8% vs 21.4%); train DD
also better. Matches the “lower factor vol” half of the hypothesis more than
the “higher Sharpe” half on this window.
4. **Survivorship / short history.** Same caveats as all current research:
today’s constituents, ~35 independent weekly windows, one post-2021 regime
dominant. Task 3 (history depth) should re-check IC stability before any
wire-in.
5. **Not shipped.** Machinery lives on the research branch; production residual
path is untouched.
---
## What a human must decide next
1. **Accept or reject** replacing `mom_12_1_resid` with `mom_12_1_sector_resid`
as the production residual (gate + 80/20 mom leg), **or** keep market residual
and treat sector residual as research-only.
2. If leaning accept: require **Task 3 history-depth** confirmation (IC era split
pre/post-2021) before any production PR.
3. Optional: run **sector-cap ≤3** A/B with full tail diagnostics (not run here).
4. **Do not** merge this verdict into main strategy docs without review.
5. Wire-in design (live sector map refresh, ETF series ops, fallback when sector
missing) is a **separate** approved engineering step.
---
## Implementation notes (research machinery)
| piece | role |
|---|---|
| `app/services/sector_map.py` | GICS→ETF map, symbol normalise, JSON load/save |
| `app/services/backtest_service.py` | multi-factor residual; `mom_12_1_sector_resid` in `_signal_values`; demean inject |
| `scripts/build_ticker_sector_map.py` | SP500 CSV + FMP gap fill |
| `scripts/fetch_sector_etfs_to_snapshot.py` | Alpaca → snapshot `benchmark_prices` |
| `scripts/run_sector_residual_research.py` | race guard, IC, optional A/B, reports |
| `data/research/ticker_sector_map.json` | persisted labels (research only) |
---
## Artifacts
- JSON: `reports/sector-residual-20260719-083356.json`
- MD copy: `reports/sector-residual-20260719-083356.md`