Building Equal-Weight Multifactor Stock Portfolios with Layered Factor Weights
Summary
The report describes a multifactor stock-selection process that first evaluates and selects robust factors, then combines them into a composite score. It builds separate models for six stock universes and compares direct selection with portfolios that select cyclical and non-cyclical stocks separately before recombining them. Factor weights are assigned in two layers: across five broad factor groups, then among factors within each group according to measured effectiveness.
Simulated portfolios use equal weights and are compared with equal-weight universe benchmarks. The report summarizes historical excess returns, benchmark-relative drawdowns, and quarterly win rates for selected large- and mid-cap universes; these are reported results, not guarantees. It also tests modest changes to portfolio size and factor weights to assess sensitivity, while noting the risk of overfitting parameter choices. The excerpt does not provide the underlying sample period, full factor definitions, or detailed implementation assumptions, which limits independent evaluation.
Key ideas
- Factor selection is tailored to each of six stock universes.
- Weights are assigned across factor groups and then across factors within each group.
- The study compares direct selection with separate cyclical and non-cyclical selections recombined into portfolios.
- Simulated portfolios are equal-weighted and measured against equal-weight benchmarks.
- Sensitivity tests vary portfolio size and factor weights, though the excerpt lacks details needed to reproduce the analysis.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.