Using PCA Loadings to Build a Zero-Equilibrium Synthetic Portfolio

Summary

The document describes an indicator that uses principal component analysis to choose coefficients for instruments in a pseudo-stationary portfolio intended to return toward zero. It frames each instrument as a dimension in a multivariate dataset and uses PCA to identify directions that capture portfolio movement. The resulting coefficients determine each instrument’s weight and direction: positive coefficients indicate buying, while negative coefficients indicate selling. Recalculation over time is proposed to maintain the synthetic portfolio’s stationarity.

The author says the computed vector values were checked against results from an R package, but cautions that PCA does not determine the signs of coefficients; those must be settled empirically. The document also mentions chart synchronization and unstable rolling loadings as possible practical issues. It provides no performance results or detailed portfolio construction, trading, or risk controls, so the proposed equilibrium behavior is not demonstrated as a profitable strategy.

Key ideas

• PCA is used to estimate coefficients for a synthetic portfolio of instruments.
• Positive coefficients correspond to long positions and negative coefficients to short positions.
• The coefficients may be recalculated to help preserve pseudo-stationarity.
• PCA loading signs are indeterminate and require empirical interpretation.
• The document reports a comparison with R output but provides no trading performance evidence.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.