Deep Learning, Predictability, and Optimal Portfolio Returns

Babiak, Mykola; Baruník, Jozef

doi:10.2139/ssrn.3688577

Cited by 3 publications

(1 citation statement)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, the computational burden increases sharply if multiple linear or nonlinear constraints are added. To address the input estimation problem, many deep-learning based methods have been proposed recently, such as (Yang, Liu & Wu, 2018), (Gu, Kelly & Xiu, 2020), (Babiak & Barunik, 2020) and references therein. To address the second and third questions, (Perrin & Roncalli, 2019) reviewed machine learning optimization approaches to solve the constrained quadratic programming problem in high dimensions.…”

Section: Literature Reviewmentioning

confidence: 99%

Asset Allocation via Machine Learning

Hong¹,

Tian²,

Yang³

et al. 2021

AFR

View full text Add to dashboard Cite

In this paper, we document a novel machine learning-based numerical framework to solve static and dynamic portfolio optimization problems, with, potentially, an extremely large number of assets. The framework proposed applies to general constrained optimization problems and overcomes many major difficulties arising in current literature. We not only empirically test our methods in U.S. and China A-share equity markets, but also run a horse-race comparison of some optimization schemes documented in (Homescu, 2014). We record significant excess returns, relative to the selected benchmarks, in both U.S. and China equity markets using popular schemes solved by our framework, where the conditional expected returns are obtained via machine learning regression, inspired by (Gu, Kelly & Xiu, 2020) and (Leippold, Wang & Zhou, 2021), of future returns on pricing factors carefully chosen.

show abstract