Maximally Machine-Learnable Portfolios

arXiv:2306.05568v2 Announce Type: replace-cross
Abstract: When it comes to stock returns, any form of predictability can bolster risk-adjusted profitability. We develop a collaborative machine learning algorithm that optimizes portfolio weights so that the resulting synthetic security is maximally predictable. Precisely, we introduce MACE, a multivariate extension of Alternating Conditional Expectations that achieves the aforementioned goal by wielding a Random Forest on one side of the equation, and a constrained Ridge Regression on the other. There are two key improvements with …

abstract algorithm arxiv collaborative econ.em extension form machine machine learning multivariate portfolio q-fin.pm q-fin.st returns risk security stat.ml stock synthetic type