Advances in Financial Machine Learning

CHAPTER 16 Machine Learning Asset Allocation

16.1 Motivation

This chapter introduces the Hierarchical Risk Parity (HRP) approach.¹ HRP portfolios address three major concerns of quadratic optimizers in general and Markowitz's Critical Line Algorithm (CLA) in particular: instability, concentration, and underperformance. HRP applies modern mathematics (graph theory and machine learning techniques) to build a diversified portfolio based on the information contained in the covariance matrix. However, unlike quadratic optimizers, HRP does not require the invertibility of the covariance matrix. In fact, HRP can compute a portfolio on an ill-degenerated or even a singular covariance matrix, an impossible feat for quadratic optimizers. Monte Carlo experiments show that HRP delivers lower out-of-sample variance than CLA, even though minimum-variance is CLA's optimization objective. HRP produces less risky portfolios out-of-sample compared to traditional risk parity methods. Historical analyses have also shown that HRP would have performed better than standard approaches (Kolanovic et al. [2017], Raffinot [2017]). A practical application of HRP is to determine allocations across multiple machine learning (ML) strategies.

16.2 The Problem with Convex Portfolio Optimization

Portfolio construction is perhaps the most recurrent financial problem. On a daily basis, investment managers must build portfolios that incorporate their views and forecasts on risks and returns. This is the primordial ...