The call
The model leans bullish on Soybeans: its score is +23 on a scale of -100 to +100, above the +25 line, and it has held this view for 112 days. Confidence is medium.
- 100% of the weighted components agree with the call.
- Speculative positioning is crowded long, which raises the risk of a sharp reversal.
Calls change only when the score moves clearly across the line: a bullish or bearish call stays until the score falls back inside ±10, so it does not flicker. A call is a view of direction over weeks, not a forecast of tomorrow.
Why: what makes up the score
| Ingredient | Reading | Weight | Points |
|---|---|---|---|
| Trend | Up 3.9% over three months and up 24.5% over twelve; price is below its 50-day and above its 200-day average. | 65% | +23.4 |
| Value (vs 5-year average) | Price is 9% above its five-year average; large gaps tend to close slowly, so this signal leans against the move. Shown for context; not in the score (it did not help in testing). | 0% | – |
| Macro drivers | How the instrument has reacted to the dollar, equities and US rates over the past year; see the drivers table below. | 35% | 0.0 |
| Score | +23 | ||
Each ingredient is scaled from -1 to +1 using only past prices and published rates; points = weight × reading × 100. The weights were set from published research before testing; an ingredient that clearly failed in the 2010-2017 test period was taken out of the score. Full method.
Price chart
Risk levels
Levels for a long idea, from recent volatility (the 14-day average true range, ATR, is 0.31 or 1.14% of the price):
The "wrong beyond" level is where the call's reasoning would no longer hold on current volatility; it is a way to think about risk, not an order. Objectives are simple multiples of that distance. Volatility now: 12.4% a year , higher than 42% of the past year's days . Moves can gap past any level.
Positioning of traders (CFTC)
Positioning is not in the score: we only have two years of weekly history, too short to test fairly. It is used for the confidence level: a call that agrees with a very crowded trade is marked down, because crowded trades can reverse fast. Full report for soybeans.
How it reacts to the big drivers
| Driver | Link over the past year | Driver over 3 months | Pushes the instrument |
|---|---|---|---|
| US dollar | 0.00 | rising | not linked |
| US equities | +0.08 | rising | not linked |
| US real yield (10Y) | −0.06 | rising | not linked |
"Link" is the correlation of 5-day moves with the driver over the past year (between -1 and +1; below 0.15 in size is ignored). The driver's 3-month direction is scaled by its own volatility. For commodities this is part of the score (35% weight).
Seasonal pattern
In October, Soybeans has averaged +0.98% and risen in 56% of the 16 years we have.
Context only, not in the score. For most markets a calendar pattern is weak and unstable; farm goods have the clearest seasonal logic (planting and harvest).
Track record: the model replayed on Soybeans
From 2010 to today (15 years), one position, rebalanced monthly, using only the data of each day, after costs of 6 basis points per switch.
| Strategy | Return a year | Risk | Per unit of risk | |||
|---|---|---|---|---|---|---|
| Follow the model's calls | −0.8% | 13.5% | -0.06 | |||
| Trend alone | −0.3% | 14.7% | -0.02 | |||
| Always long (no calls) | +0.6% | 18.2% | 0.03 | |||
| The model's calls, in two halves | ||||||
| 2010 to 2017 | −4.0% | 12.4% | -0.33 | |||
| 2018 to today | +1.6% | 14.2% | 0.11 | |||
On a single instrument luck dominates: a model that is right a little more than half the time still has long losing stretches. The pooled result across all commodities is on the commodities page. This is a replay of rules, not a live record. The live log of every daily call started on 16 Oct 2026; fund proxies include the funds' own roll costs .
| Date | Changed to | Score | Price then |
|---|---|---|---|
| 26 Jun 2026 | Bullish (was neutral) | +25 | 24.50 |
| 9 Jun 2026 | Neutral (was bullish) | +10 | 24.09 |
| 5 Feb 2026 | Bullish (was neutral) | +29 | 22.96 |
| 12 Dec 2025 | Neutral (was bullish) | +9 | 22.52 |
| 20 Oct 2025 | Bullish (was neutral) | +27 | 22.06 |
| 10 Oct 2025 | Neutral (was bullish) | −7 | 21.56 |
| 8 Oct 2025 | Bullish (was neutral) | +26 | 21.92 |
| 22 Sep 2025 | Neutral (was bullish) | −4 | 21.67 |
| 15 Aug 2025 | Bullish (was neutral) | +28 | 22.18 |
| 25 Jun 2025 | Neutral (was bullish) | −8 | 21.58 |
*Price move afterwards in the direction of the call (positive = the call was right); blank for neutral calls and for recent changes without enough days yet. Shows hits and misses alike.
About this call
Soybeans is a commodity market. No futures data on our plan, so this uses the Teucrium Soybean Fund (SOYB) as a proxy. Fund prices follow futures, include the cost of rolling contracts and can drift from the spot price. The call comes from one scoring model used for every instrument in the same way, described on the method page. It reads prices, interest rates and (for context) trader positioning; it does not read news or predict events, and it can be wrong for long periods.
Fund proxy. Our data plan does not include futures prices, so this uses an exchange-traded fund that holds futures. Such funds lose or gain from the cost of rolling contracts (contango and backwardation), so their price can drift away from the spot price over time.
Risk warning. Educational research, not personal advice or an invitation to trade. Forex and commodity trading, especially with leverage, carries a high risk of losing money quickly; most retail accounts that trade leveraged products lose money. Past behaviour of a model does not predict the future.