The idea worth investigating
A recently listed stock should not erase years of observations for the rest of a portfolio. Bongiorno and Villassero build a covariance estimator around incomplete histories and train it on realized portfolio risk.
The full analysis examines the study and the practical question behind it: A neural estimator uses unequal stock histories without discarding the longer records. The authors report a sizeable risk difference.
Paper-based analysis; no independent house test has been completed.
Paid analysis on Substack
See what changes the investment case.
The headline is the starting point. The subscriber analysis takes you through:
- The estimator and its comparison set
- Return, drawdown and cost evidence
- The replication controls we would require
AI assists curation and drafting. The research status distinguishes paper reviews from house tests. Read our research approach.