· Analytic
LH Pork Cutout Signal (5-Day Smoothed)
USDA AMS five-day-smoothed pork carcass cutout year-over-year, z-scored and tanh-bounded, as a slow-confirming demand-regime read on Lean Hogs forward returns.
At a glance
Current reading
-0.941
Low-Cutout extreme-negative, constructive band
Signal state
Extreme NEG
phase -1, 37 trading days in state
Sample
3,009 daily obs since 2015
AMS LM_PK602 avg_5day_carcass
Historical IC
-0.0154
Spearman vs LH fwd60d, p = 0.14 (NOT significant)
Baseline LH fwd60d
+0.41%
Unconditional mean
Low-Cutout fwd60d
+3.26%
+2.85 pp above baseline, current firing band
As of Oct 30, 2026. Updated nightly.
OBJECTIVE
Every afternoon the USDA Agricultural Marketing Service publishes the wholesale pork carcass cutout, dollar per hundredweight, broken down by primal cut. Alongside the raw daily carcass print the report publishes a five-day moving average that flattens the Monday-vs-Friday pattern and the single-plant reporting idiosyncrasies that bounce the raw number two to five dollars day-to-day. This signal reads the five-day-smoothed cutout year-over-year, z-scores it on two years of history, and bounds the result between plus and minus one. The resulting composite is slower to turn than the raw-daily sibling but less prone to false-breakout tail readings on single-day prints. In January 2021 the signal pinned at minus 0.52 in the Low-Cutout tail after the post-COVID holiday-demand bulge dissipated; lean hog futures rallied 50 percent over the next sixty days on structural supply tightening. In May 2023 another Low-Cutout reading at minus 0.51 preceded a 38 percent rally as the export-tempo wound down. The memorable twist: this is the weakest signal in the eight-member Lean Hogs batch. The 36-year Spearman IC is minus 0.015 at p = 0.14 and does not reject the null. The signal functions as a tail-asymmetry reader (Low-Cutout tail constructive, High-Cutout tail bearish) rather than a continuous directional predictor. The dual signal with the raw-daily sibling catches shocks through the raw and confirms through the smoothed only when the move sustains. Read on for the four-case history, the state the signal reads right now, and why the smoothed read should carry 0.25 to 0.33 of the raw-daily sibling weight.
LIVE CHART
LH Pork Cutout Signal (5-Day Smoothed)
Composite reads -0.941 as of October 30, 2026, in the Low-Cutout extreme-negative band, 37 trading days running since September 10, 2026. The 5-day smoothed pork cutout has faded through H2 2026, consistent with the raw-daily sibling. Historical state-conditional edge for this band is +2.85 pp above the +0.41% baseline — modestly constructive forward backdrop.
COMPOSITE
-0.941 / tanh
STATE
Extreme Neg
PHASE
-1
FWD 60d
+9.93% (baseline +1.59%)
SAMPLE N
9,049 days
STATE-CONDITIONAL EDGE
Forward 60-day returns by state
FORWARD 60-DAY RETURNS BY STATE
Mean forward-60-day benchmark return per composite state. Baseline (horizontal line) is the unconditional sample mean. Bars above the line are the constructive bands; bars below are the bearish bands.
TODAY’S PLAYBOOK READING
STATE
Extreme Neg
STATE AND HISTORY
Low-Cutout extreme-negative firing, 37 trading days running since September 2026. State-conditional fwd60d LH mean is +3.26%, +2.85 pp above the +0.41% baseline.
WHY WEAKEST IN BATCH
5-day smoothing lags shocks by about a week versus the raw-daily sibling. Aggregate Spearman IC does not reject the null at p = 0.14; only the extreme tails carry informational content.
HOW TO POSITION
Treat as slow confirmation of the raw-daily cutout signal, not standalone. The current Low-Cutout firing is modestly constructive on history. Pair with the raw-daily cutout sister signal (raw-daily cutout) and CFTC positioning for the full read.
WHAT THE CHART SHOWS
The composite sits at -0.941 in the Low-Cutout extreme-negative band, 37 trading days running since September 10, 2026. The blue signal line has moved into deep-negative territory as the 5-day-smoothed cutout has faded below year-ago. CME lean hogs (orange) have traded range-bound in the $56-$62 zone. The engine state-conditional edge for this band is +2.85 pp above the +0.41% baseline. The rolling IC pane shows the 252-day Spearman has drifted negative, consistent with the signal long-term empirical direction (inverted vs engine semantic declaration).
TOP INPUTS FIRING
- Primary composite -0.941 State Extreme NEG; 37 trading days running since September 10, 2026.
- Raw z-score -1.74 Z-score of 5-day-smoothed pork cutout YoY, on a 2-year rolling window with 60-day minimum, tanh-bounded. Note: 5-day smoothing is applied by the USDA AMS source, not by the signal engine.
- State-conditional edge: +2.85 pp Low-Cutout extreme-negative historical fwd60d LH mean +3.26%, baseline +0.41% (edge +2.85 pp). 11.3% of sample sits in this band. Tail-asymmetry reader; aggregate IC is not significant.
THE TAKEAWAY
What this means for you today
THE DEMAND-REGIME CALL
Composite -0.941, Low-Cutout extreme-negative band. The 5-day smoothed pork cutout has run below year-ago through H2 2026, consistent with the raw-daily sibling reading.
THE EMPIRICAL CONTEXT
Low-Cutout extreme-negative historically delivers mean fwd 60-day LH of +3.26%, +2.85 pp above baseline. 11.3% of the sample sits in this band. Modestly constructive forward backdrop.
THE HONEST CAVEAT
Signal aggregate IC is not statistically significant (p = 0.14). This is a tail-asymmetry reader, not a continuous predictor. The sister raw-daily cutout signal carries the significant IC and should drive sizing; this signal confirms the regime.
THE REGIME MAP
The three states, forward returns and sample share
Computed from 8,986 trading days with observable LH fwd60d (AMS data begins 2015-01-02; pre-2015 state readings are artifacts). Baseline LH fwd60d (unconditional): plus 0.41 percent mean, minus 0.03 percent median, 11.81 percent standard deviation, 49.8 percent negative.
| State | Phase | Share | Fwd 60d | HAC t | Edge vs baseline | Last firings |
|---|---|---|---|---|---|---|
| High Cutout | +1 | 11.5% (1039 d) | -7.45% | -9.05pp | Jul 2026, May 2025, Oct 2024 | |
| Normal | 0 | 74.7% (6760 d) | +3.51% | +1.92pp | Sep 2026, Aug 2026, Jul 2026 | |
| Low Cutout TODAY | -1 | 13.8% (1250 d) | +9.93% | +8.34pp | Sep 2026, Aug 2026, Dec 2025 |
The historical pattern
Signature episodes in the sample
THE TRACK RECORD
State changes
| State | Start | End | Duration | Fwd 60d LH |
|---|---|---|---|---|
| Neutral | 10/30/2024 | 10/30/2024 | 1d | +3.76% |
| Positive | 10/31/2024 | 11/08/2024 | 7d | +6.40% |
| Neutral | 11/11/2024 | 11/18/2024 | 6d | +1.02% |
| Negative | 11/19/2024 | 02/28/2025 | 69d | +3.83% |
| Neutral | 03/03/2025 | 03/21/2025 | 15d | +0.68% |
| Negative | 03/24/2025 | 04/29/2025 | 26d | +4.07% |
| Neutral | 04/30/2025 | 05/19/2025 | 14d | +14.86% |
| Positive | 05/20/2025 | 10/10/2025 | 100d | +8.53% |
| Neutral | 10/13/2025 | 10/20/2025 | 6d | +3.99% |
| Negative | 10/21/2025 | 12/16/2025 | 40d | +3.03% |
| Neutral | 12/17/2025 | 12/26/2025 | 7d | -0.09% |
| Negative | 12/29/2025 | 07/09/2026 | 132d | -6.22% |
| Neutral | 07/10/2026 | 07/21/2026 | 8d | +2.63% |
| Positive | 07/22/2026 | 08/14/2026 | 18d | +3.26% |
| Neutral | 08/17/2026 | 08/28/2026 | 10d | |
| Negative | 08/31/2026 | 08/31/2026 | 1d | |
| Neutral | 09/01/2026 | 09/09/2026 | 6d | |
| Negative | 09/10/2026 | 10/30/2026 | 37d |
Scroll inside the table for the full history. Forward 60-day LH is measured from each run’s start date; a reader cannot trade off a start-date they only identify in hindsight, so this is a transparency log, not an alpha claim. Asterisked (*) returns are partial. The run is less than 60 trading days old. The full 60-day comparable fills in as more data arrives.
What this measures
The signal pulls the USDA AMS Daily Pork Cutout report (LM_PK602) and reads the pre-smoothed `avg_5day_carcass` field directly (the AMS report publishes this five-day moving average alongside the raw daily carcass value). The signal computes year-over-year percent change on the smoothed series, z-scores the result on a 504-day (2-year) rolling window with a 60-day minimum population, and bounds the output with tanh to plus or minus one. The state machine applies thresholds at plus or minus 0.2 (moderate) and plus or minus 0.5 (extreme).
Why it matters
Why the 5-day-smoothed cutout exists as a separate signal
The raw daily wholesale pork cutout can swing two to five dollars per hundredweight day-to-day on packer reporting idiosyncrasies, holiday-week distortions, or single-plant reporting delays. The USDA AMS report publishes a 5-day moving average alongside the raw daily carcass value as a trend-indicator for industry traders. This signal reads the smoothed version directly. In backtests the smoothed read is slower to turn but less prone to false-breakout tail readings on single-day prints. During supply-shock onsets (COVID packer closures, export shocks) the raw signal catches the shock in real time while the smoothed version lags by about a week; the dual signal CONFIRMS the regime only when the move sustains past the smoothing window.
Why the aggregate IC does not reject the null
The smoothing slows the signal enough that the 36-year Spearman IC against LH fwd60d is minus 0.015 (p = 0.14), which does not reject the null at the 5 percent threshold. The sister raw-daily signal (IC minus 0.056, p = 1.85e-7) is strongly significant. This signal functions empirically as a tail-asymmetry reader: the Low-Cutout extreme-negative tail delivers +2.85 pp above baseline and the High-Cutout extreme-positive tail delivers minus 0.94 pp below baseline. The middle bands sit near baseline with no informational content.
How to use this signal today
Treat as slow confirmation of the raw-daily cutout signal, never a standalone sizing input. The current Low-Cutout extreme-negative firing is modestly constructive on history (+2.85 pp above baseline), consistent with the raw-daily sibling and the current regime of persistent below-year-ago pork wholesale prices. Pair with the raw-daily cutout signal, CFTC commercial positioning, and the Iowa margin-pressure signal for the full LH read. For composite weighting the smoothed signal should carry 0.25 to 0.33 of the raw-daily weight given the lower IC.
GO DEEPER
Want the full depth?
The research brief walks through the USDA AMS 5-day-smoothed pork cutout series vs CME Lean Hogs forward returns, documents why this is the weakest signal in the LH batch (p = 0.14, does not reject null), and sets out why the Low-Cutout extreme-negative tail delivers a modestly constructive forward edge while the aggregate signal does not.
Related signals
Not investment advice · The analysis on this page is informational and educational. Signal readings, historical case figures, and empirical statistics are derived from publicly available data and are provided without warranty. Hypothetical performance results have inherent limitations, including the benefit of hindsight. Readers who intend to trade should consult a licensed investment professional and see the research brief for the full disclaimer.
Last refreshed Oct 31, 2026 01:45 PM ET