AgenticInvestor

Rapeseed/Colza Futures

Agriculture · Monthly series · CM-ECO1.EURONEXT

Latest, October 2026

555.25 EUR/TNE

+3.4% from September 2026

Open interactive chartRapeseed/Colza Futures in the app

941642.9344.8November 2016October 2027
History through October 2026, the forecast path to October 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for October 2027: 554.88 EUR/TNE, with an 80% interval of 454.54 EUR/TNE to 655.23 EUR/TNE.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
November 2026554.88 EUR/TNE519.92 EUR/TNE589.84 EUR/TNE
December 2026554.88 EUR/TNE486.96 EUR/TNE622.80 EUR/TNE
January 2027554.88 EUR/TNE512.10 EUR/TNE597.66 EUR/TNE
February 2027554.88 EUR/TNE487.19 EUR/TNE622.57 EUR/TNE
March 2027554.88 EUR/TNE464.38 EUR/TNE645.38 EUR/TNE
April 2027554.88 EUR/TNE440.72 EUR/TNE669.04 EUR/TNE
May 2027554.88 EUR/TNE420.73 EUR/TNE689.03 EUR/TNE
June 2027554.88 EUR/TNE449.63 EUR/TNE660.13 EUR/TNE
July 2027554.88 EUR/TNE455.27 EUR/TNE654.49 EUR/TNE
August 2027554.88 EUR/TNE435.61 EUR/TNE674.15 EUR/TNE
September 2027554.88 EUR/TNE449.19 EUR/TNE660.57 EUR/TNE
October 2027554.88 EUR/TNE454.54 EUR/TNE655.23 EUR/TNE

Model: Exponential smoothing (statistical). Forecast generated 2026-11-14.

AI confidence

Mixed evidence

The tests show no consistent, material advantage over the no-change baseline.

Model: Exponential smoothing (statistical)

Accuracy vs naive
0%Matches the no-change baseline over 6 tests (6 tests, 3 won)
Direction
54%No clear edge over a coin flip (39 of 72 calls right in 6 tests)
Turning points
0 of 32Anticipated no turn, as the no-change baseline does (32 turns in 6 tests, 0 without a turn)
Error vs baseline
About the sameError ratio 1.00; 1.00 is a tie.
Tests won
3 / 6Complete recent tests excluded from model selection; ties count as no win.
Test period
2020-11-01 to 2026-10-0112 observations ahead per test.
80% band coverage
80%Observed outcomes inside the band across all stored test windows.
How this assessment is made

AI confidence describes historical evidence for this forecast, not a probability of being correct. Each backtest fits on data available before its test window. The baseline carries the last value forward. Supported evidence requires at least six complete, non-overlapping tests, an error ratio below 0.90 (rounded to two decimals), and wins in a majority of tests. Ratios from 0.90 to below 1.10 are on par; 1.10 or above is weak evidence. Inconsistent wins produce mixed evidence. For a selected model, only the recent tests excluded from model selection determine this label. These are historical simulations using the available data, not a live trading track record; revisions and foundation-model pretraining can limit how closely they reproduce a past decision. Past performance can change.

Replay past tests

Model comparison

4 of 5 models evaluatedModels are selected on older tests and evaluated on separate recent tests. Some candidates failed or returned incomplete tests; the table shows which. An eligible nightly batch can compare four classes, subject to call budgets and retry limits.

Models tested

Exponential smoothing scored lowest on the 6 older tests (1.00) and was chosen. The 6 recent tests played no part in the choice and give its grade (1.00). The search for a model that beats the naive forecast on both sets of tests goes on. Scores are MASE: a model's errors divided by the naive forecast's, so 1 is a tie.

3 model classes completed the tests: Statistical, Foundation model, Machine learning.

Every model tested on this series.
ModelClass and computeOlder testsRecent testsRole
Exponential smoothing (statistical)Statistical · CPU1.001.00Serving
Naive forecast (last value held)Benchmark · CPU1.001.00Benchmark
Agentic Investor TSFM (foundation model)Foundation model · CPU1.010.96Tested
State-space model, 167M (foundation model)Foundation model · CPU1.080.88Tested
Gradient-boosted trees (machine learning)Machine learning · CPU1.441.01Tested
Hierarchical neural network (neural network)Neural network · CPUn/an/aDid not run

Uses ci-proto, released by Continuous Intelligence. Continuous Intelligence does not endorse or approve this product or service. (ci-proto is shown as State-space model, 167M.)

Reading

It is above 86% of the 119 earlier readings since November 2016.

Written from the figures by a fixed template; no AI model is involved.

Recent history (24 observations)
The 24 most recent observations, newest first.
PeriodValue
October 2026555.25 EUR/TNE
September 2026536.75 EUR/TNE
August 2026544.25 EUR/TNE
July 2026513.00 EUR/TNE
June 2026505.25 EUR/TNE
May 2026524.25 EUR/TNE
April 2026520.75 EUR/TNE
March 2026514.25 EUR/TNE
February 2026487.00 EUR/TNE
January 2026472.75 EUR/TNE
December 2025453.25 EUR/TNE
November 2025483.25 EUR/TNE
October 2025480.50 EUR/TNE
September 2025466.00 EUR/TNE
August 2025462.50 EUR/TNE
July 2025477.50 EUR/TNE
June 2025467.50 EUR/TNE
May 2025474.50 EUR/TNE
April 2025462.00 EUR/TNE
March 2025516.75 EUR/TNE
February 2025532.75 EUR/TNE
January 2025515.50 EUR/TNE
December 2024511.25 EUR/TNE
November 2024507.75 EUR/TNE

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Agriculture