Finding 2196Emerging EvidenceValidation V0
This paper introduces a novel machine learning-based 'characteristic-managed momentum' (CMM) strategy, which flexibly weights past returns to outperform traditional momentum. Its originality lies in data-driven, conditional weighting, revealing that only select daysoften with large returns or newsmatter most. Robust empirical results offer compelling insights for both academic research and trading applications.
78%Confidence
1Evidence objects
v1Version
DraftStatus
Evidence trail
Supporting78% linkage confidence
This paper introduces a novel machine learning-based 'characteristic-managed momentum' (CMM) strategy, which flexibly weights past returns to outperform traditional momentum. Its originality lies in data-driven, conditional weighting, revealing that only select daysoften with large returns or newsmatter most. Robust empirical results offer compelling insights for both academic research and trading applications.
key_findings bullet 4 · key_findings
Inspect source: All Days Are Not Created Equal: Understanding Momentum by Learning to Weight Past Returns →This Finding was extracted from the configured corpus. It is versioned, traceable, and may evolve through editorial review or new corpus evidence.