Aluminium flat-rolled products are not immune to the latest market turmoil. We conducted a Monte Carlo simulation update to better understand the impact of the current risk environment on the 1050 conversion fee forecast in Europe. The same ensemble decision tree regression model, that we developed last year to assess the monthly 1050 common alloy conversion fee, was applied but this time we focused on upside rather than downside risks.
The LME 3-month aluminium price has moved to multi-year highs during the conflict in the Middle East, Rotterdam ingot duty-paid premia have surged, and oil prices have remained elevated. This raises the risk that higher raw material and energy costs can feed into conversion fees and broader inflationary pressure in Europe. Many are now asking – what are the implications and outlook for the European conversion fees under increasingly uncertain conditions?
In such a volatile and unpredictable environment, scenario analysis and simulations can provide additional perspective. In this Insight, we describe the updated results of the Monte Carlo simulation conducted using the regression model for predicting 1050 European conversion fees developed in a previous Insight. We do not repeat the full methodology in this Insight, but instead focus on the revised scenario design and the implications for the 1050 fee and for the 5754 sheet alloy.
Update of the regression model and exploratory analysis
To run the Monte Carlo simulation, we updated the regression model with the latest available actuals for the six input features. The monthly inputs remain the same – European stainless steel sheet price, LME 3-month aluminium price, Rotterdam ingot duty-paid premium, USD/EUR exchange rate, Economic Sentiment Index (ESI) and inflation, measured by the Harmonised Consumer Price Index (HICP).
Model “focus” shifted more to stainless steel and ingot premium
The “focus” of the model, measured by feature importance, has shifted since our earlier Insight.Compared with late 2024, the importance of the LME 3-month aluminium price has fallen sharply, while 304 stainless steel and Rotterdam ingot duty-paid premium have become the two dominant inputs in this latest assessment. USD/EUR remains of only marginal importance, which allows the exchange rate to vary within the updated stress scenario rather than imposing an additional FX shock.
This shift is useful for interpreting the latest market environment. The model is now attaching more weight to downstream cost and premium conditions than to the outright aluminium price alone. In that sense, the current combination of high metal prices and sharply higher premia is more relevant for the fee outlook than a simple read across from LME levels alone.
1050 conversion fee has a very strong correlation with the 5754 sheet alloy, while plate fees constitute a completely separate category.
The broader conclusions from our earlier exploratory analysis remain unchanged. The 1050 conversion fee has a very strong relationship with the 5754 sheet fee, so the 1050 simulation still provides a useful indication for5754 on an ex-premium basis, using the long-term average spread established in our previous Insight.
However, the plate conversion fees continue to behave as a separate category. Compared with commodity‑grade sheet alloys such as 1050 and 5754, plate products retain higher value‑added content and should therefore be better placedto sustain short-term market turbulence, even if they are not completely immune from wider uncertainty.
Monte Carlo simulation for 1050 fee and indicationfor 5754 alloy
To generate updated predictions for the 1050 conversion fee, we use the same trained regression model and the Monte Carlo framework discussed earlier. In this update, we ran three different simulations:
- Base simulation: The standard scenario where all input features are varied based on their historical distributions and dependence structure.
- Single-factor stressed scenario: Only one input feature, the Rotterdam ingot duty-paid premium, is fixed at the 99th percentile, while all other features are allowed to vary.
- Multi-factor extreme-case scenario: The LME 3-month aluminium price and Rotterdam ingot duty-paid premium are fixed at the 99th percentile, HICP is fixed at the 95th percentile, and 304 stainless steel is fixed at the 85th percentile. CRU expects little stainless steel disruption or direct impacts across the stainless steel market, so we ran 304_stainless at the 85th percentile rather than at an extreme level. The USD/EUR exchange rate and ESI are allowed to vary, conditional on the historical dependence structure.
The results of each simulation are summarised in the chart below. The main takeaway is that at the February 2026 level of €747 /t (excluding the ingot premium) the 1050 conversion fee sits slightly above the mean predicted by both the base simulation and the single-factor ingot premium stress case.
Under the base simulation, the mean predicted fee is around €725 /t, while in the single-factor stress case (with the ingot premium fixed at the 99th percentile) the mean prediction is around €713 /t. This indicates that a higher ingot premium on its own does not translate into a materially higher 1050 conversion fee on an ex-premium basis.
The picture changes significantly under the multi-factor extreme-case scenario. In this case, the mean predicted fee (excluding premium rises) is around € 1,113/t, with a 5th–95th percentile range of roughly €888–1,229/t. All simulated outcomes in this stress case remain above the current February 2026 fee level. This suggests that if very high LME prices, sharply higher ingot premia, and broader inflation pressures in Europe persist together, the upside risk to the 1050 conversion fee would become substantial.
Current market conditions only partially align with this stress set-up. LME aluminium is already close to the upper tail of the historical distribution and ingot premia are elevated, but stainless steel prices and inflation remain below the stressed levels imposed in the multi-factor case. The extreme-case scenario should therefore be viewed as a forward-looking stress test rather than as a reflection of current market conditions.
The same logic applies to the 5754 conversion fee, using the long-term average spread to the 1050 fee of €181/t. The close relationship between the two alloy fees means the 1050 simulation remains a useful guide to the direction and scale of risk for 5754 in Europe.
Contact us to find out how CRU can help you navigate these market conditions.
