A prevailing assumption in trend following is that highly correlated assets should not be traded together, as they are unlikely to provide diverse opportunities. This assumption overlooks a critical distinction: the difference between price correlations and trade correlations. Examining the behaviour of different trend following systems applied to highly correlated assets reveals why system diversification matters and how it shapes the geometric return outcomes of a trend following portfolio.
Understanding the Importance of Trade Correlations
At first glance, the price series of Brent and Crude Oil appear nearly identical, leading many to believe that trading both is redundant (see Figure 1). This superficial analysis overlooks the critical distinction between price correlations and trade correlations, which are essential for Outlier Hunters. 
Source: Finvis
Figure 1: Comparison between the price series of Brent and Crude
The Misconception of Diversification Limits
A common belief in portfolio management is that diversification benefits diminish after a certain point, often cited as around 60 uncorrelated assets, based on the Central Limit Theorem. The theorem suggests that as sample sizes grow they approximate a normal distribution, implying an optimal level of diversification. The benefits of diversification are said to follow the square root law, where the reduction in portfolio risk is proportional to the square root of the number of assets, and the incremental benefit of each additional asset diminishes as the portfolio grows. The 50th asset contributes less risk reduction than the 5th.
This framework falters when applied to non-linear distributions dominated by Outliers. A common error is assuming that diversification limits apply uniformly across all investment strategies. That assumption reflects the properties of strategies that do not capture beneficial volatility, mean reversion being the clearest example. Mean reversion strategies are characterised by negative skew: small profits are frequent, large gains are rare, and occasional large losses can occur. Smooth return streams quickly become correlated in this environment, and the uncorrelated large losses cause material harm to the portfolio. Diversification offers limited structural benefit under these conditions.
Trend following operates in the opposite territory. The target is beneficial Outliers: rare, large price moves that generate disproportionate positive returns. Financial markets exhibit fat tails and skewed distributions where extreme events occur more frequently than normal distribution models predict, and it is precisely these events that trend following is designed to capture. By diversifying across a larger number of assets, the opportunity set for capturing Outliers expands. The more diverse the portfolio, the higher the probability of encountering assets experiencing significant trends at any given time. Diversification also spreads exposure across uncorrelated markets, reducing the impact of any single asset’s poor performance while preserving full participation in the beneficial volatility that drives long-term returns. Outlier Hunters thrive on uncertainty. Diversification across a broad array of markets enhances the probability of being positioned in the market that produces the next extreme move, which is the foundation of trend-following profitability.
These Outliers are less correlated with each other than the steady return streams of negatively skewed strategies, which means diversification in trend following does not reach a point of diminishing structural value. The traditional view of diversification limits, rooted in the Central Limit Theorem and the square root law, does not hold in the context of Outlier Hunting. For an Outlier Hunter, there is no practical limit to diversification. The broader and more diversified the portfolio, the greater the probability of capturing those rare, high-impact events that drive long-term geometric return outcomes.
Exploring System Dispersion and Outliers
To illustrate this, ten identical hypothetical trend following models with the same parameter settings were applied to both Brent and Crude across a 24-year period. The expectation would be that applying the same models to a highly correlated pair of price series produces a highly correlated trade result. The data shows otherwise. The models used, both long and short, were popular trend following models with medium to long-term parameter sets: the Donchian Breakout System (DON), moving average crossover system (MAT), regression line breakout system (REG), Darvas Box breakout system (BOX), the Bollinger Band Retracement Entry into Trend system, and the Bollinger Band Breakout system (BBB).
Figure 2: 10 Identical Trend Following Models applied to Brent and Crude
When we look at the performance of these models on Brent: 
Figure 3: 10 Trend Following Models applied to Brent
The returns in Figure 3 exhibit significant dispersion, ranging from poor to excellent performance. This variance arises from the unique interactions between each system and the price series. Each system is not in the market at all times, participating only when trends become material in nature. The small differences in price and the way each system responds to its variables produce many different and disparate outcomes.
A practical illustration of the danger of cherry-picking from backtests: the best performer from a 2010 backtest was a mid-range performer by 2020, while a mid-range performer in 2010 had become the best performer by 2020. This is the nature of selecting the best system from historical data, and why an ensemble approach deploying all systems is a materially more robust method than concentrating on a single cherry-picked model. Figure 4 revisits the Brent return streams with additional detail to examine the specific influence that Outliers have in creating this dispersion.
Figure 4: 10 Trend Following Models applied to Brent: The Impact of Outliers
The major jump-up steps in Figure 4 highlight the Outliers: those rare but significant events that certain systems capture while others miss. These Outliers are the dominant drivers of performance dispersion and the primary mechanism through which correlation properties between systems are reduced. They also demonstrate the importance of using an ensemble of systems to avoid the Type 2 error of missing these key opportunities entirely. When all systems miss an Outlier, the return streams converge and dispersion collapses.
Comparing Brent and Crude Systems
Consolidating the ten return streams into a sub-portfolio for Brent yields a robust equity curve with offset drawdowns and a strong overall return: 
Figure 5: 10 Trend Following Models applied to Brent: Sub Portfolio Result
However, applying the same systems to Crude reveals stark differences (refer to Figure 6): 
Figure 6: 10 Trend Following Models applied to Crude: The Impact of Outliers
Despite the high price correlation between Brent and Crude, the outliers in each return series and resulting performance are markedly different. This discrepancy underscores the impact of small variations in price series on Outlier events, a phenomenon akin to the butterfly effect in non-linear systems.
Subportfolio Comparison: Brent vs. Crude
When comparing the sub-portfolios of Brent and Crude using the same systems, the results therefore diverge significantly: 
Figure 7: Subportfolio Comparison Between Brent and Crude
Where the price correlation comparison showed Brent and Crude as near-identical, the return distribution comparison reveals how different they actually are. The differences are substantial, driven by the unique Outlier events in each market. Trading both Brent and Crude with the same trend following models is not redundant. Their trade results are uncorrelated despite their price correlations, and that uncorrelated character is precisely what makes both worth holding. It is worth noting that both subportfolios were highly correlated at inception, having not yet captured an Outlier. The dispersion began diverging in January 2003, when Brent latched onto an Outlier that Crude did not participate in.
The analysis challenges the traditional view of diversification limits in trend following portfolios. In a market environment dominated by Outliers, the Central Limit Theorem’s square root law does not define the boundary of diversification’s value. The more diversified the portfolio, the better positioned it is to capture those rare, impactful events that drive long-term geometric return outcomes. For Outlier Hunters, there is no theoretical limit to diversification. Maximal diversification enhances correlation offsets, increases the frequency of Outlier capture, and harnesses the lifting power that makes classic trend following a structurally superior approach to long-term wealth compounding.