🤖 AI Summary
This work addresses the limitation of conventional deep learning approaches for stock ranking, which typically produce a single alpha signal and lack explicit control over correlations among multiple alphas, resulting in insufficient portfolio diversity. The authors propose MAPLE, a novel framework that, within a single training run, jointly incorporates a unified capacity-scaled prediction head, an extreme-rank weighted listwise loss, and an explicit diversity regularizer to enable controllable generation of multiple alpha signals with desired correlation structures—all within a single model. Notably, MAPLE achieves this without increasing architectural complexity and is compatible with various backbone networks. Evaluated across four major equity markets in the U.S., China, and Japan, MAPLE significantly outperforms nine baselines, achieving up to 55× fewer parameters and 2.5× faster training while improving Sharpe ratios by 10–23% and Calmar ratios by 17–43%.
📝 Abstract
Classical alpha mining achieves strong risk-adjusted returns by combining many low-correlated predictive signals, yet deep learning stock-ranking methods typically produce a single alpha per stock, rely on increasingly complex architectures with diminishing gains, and obtain diversity only through separate models or implicit routing, without explicitly controlling inter-alpha correlation. We introduce MAPLE (Multi-Alpha Position-aware Listwise Ensembling), a backbone-agnostic framework that recovers this diversity principle within a single training pass. MAPLE combines a unified, capacity-scaled prediction head with an extreme-rank weighted listwise ranking loss and a diversity regularizer that explicitly penalizes pairwise correlation across alphas. Across four equity markets spanning the US, China, and Japan, MAPLE achieves the best average Sharpe and Calmar ratios among nine baselines, using up to 55x fewer parameters and 2.5x less training time, and generalizes across five backbone architectures with Sharpe and Calmar Ratio gains of 10-23% and 17-43%, respectively. Behavioral analysis further shows why each component works: the unified head already reduces inter-alpha correlation before any diversity loss is applied, and the extreme-rank loss lets diversity regularization improve rather than erode per-alpha ranking quality as capacity scaling sustains this balance at scale. These results show that principled loss design and capacity allocation, rather than architectural complexity, drive diverse and effective multi-alpha generation.