Public research brief
Two stocks can move together for reasons that a raw correlation cannot separate.
The MINGLE study asks whether a portfolio should group stocks by their underlying risk exposures rather than simply by recent co-movement. It learns a factor model and a network of related assets together, allowing each estimate to constrain the other.
The investment case is better diversification with less sensitivity to noisy relationships. That is a different claim from predicting the next market drawdown.
Full analysis on Substack
Follow the evidence further.
The complete review examines the findings, implementation limits, and research questions beyond this public brief. Access and subscriptions are handled on Substack.
Continue reading on Substack ↗View subscription optionsAI assists curation and drafting. The research status distinguishes paper reviews from house tests. Read our research approach.