🤖 AI Summary
This paper addresses the challenge of constructing robust multi-strategy portfolios that consistently outperform the best single strategy in long-term investment. To overcome the limitations of conventional approaches—namely, reliance on statistical assumptions and parametric market distribution models—we propose a preference-driven, distribution-free framework grounded in preference-order modeling. Our method formulates portfolio optimization without assuming finite samples or specific return distributions, enabling composition over arbitrary (including infinite) strategy sets. We further develop an online wealth-maximization algorithm and its accelerated variant. Empirical results demonstrate that the proposed portfolio strictly dominates the best-performing individual strategy in cumulative returns; the accelerated version achieves substantially higher returns with only a marginal reduction in the Sharpe ratio. The core contribution is the first unified, robust, and scalable nonparametric paradigm for strategic portfolio decision-making.
📝 Abstract
This paper investigates the problem of ensembling multiple strategies for sequential portfolios to outperform individual strategies in terms of long-term wealth. Due to the uncertainty of strategies' performances in the future market, which are often based on specific models and statistical assumptions, investors often mitigate risk and enhance robustness by combining multiple strategies, akin to common approaches in collective learning prediction. However, the absence of a distribution-free and consistent preference framework complicates decisions of combination due to the ambiguous objective. To address this gap, we introduce a novel framework for decision-making in combining strategies, irrespective of market conditions, by establishing the investor's preference between decisions and then forming a clear objective. Through this framework, we propose a combinatorial strategy construction, free from statistical assumptions, for any scale of component strategies, even infinite, such that it meets the determined criterion. Finally, we test the proposed strategy along with its accelerated variant and some other multi-strategies. The numerical experiments show results in favor of the proposed strategies, albeit with small tradeoffs in their Sharpe ratios, in which their cumulative wealths eventually exceed those of the best component strategies while the accelerated strategy significantly improves performance.