Asset Allocation via Machine Learning

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.

Hybrid quantum investment optimization with minimal holding period

In this paper we propose a hybrid quantum-classical algorithm for dynamic portfolio optimization with minimal holding period. Our algorithm is based on sampling the near-optimal portfolios at each trading step using a quantum processor, and efficiently post-selecting to meet the minimal holding constraint. We found the optimal investment trajectory in a dataset of 50 assets spanning a 1 year trading period using the D-Wave 2000Q processor. Our method is remarkably efficient, and produces results much closer to the efficient frontier than typical portfolios. Moreover, we also show how our approach can easily produce trajectories adapted to different risk profiles, as typically offered in financial products. Our results are a clear example of how the combination of quantum and classical techniques can offer novel valuable tools to deal with real-life problems, beyond simple toy models, in current NISQ quantum processors.

Distribution Characteristics of Multivariate Financial Assets Return based on Mathematical Model

For the non-normality and time variability of the distribution of multivariate financial assets return, a dynamic model of the distribution of multivariate financial assets return based on mathematical model is constructed in this paper. AR(1)-DCC(1,1)-GARCH(1,1) model reflects dynamic characteristics of conditional expectation and conditional variance of multivariate financial assets return. It solves the problem that restricts the in-depth research on high order dynamic portfolio optimization, which is the estimation of conditional coskewness matrix and conditional cokurtosis matrix. By constructing a multi-dimensional fluctuation model with biased t distribution, conditional asymmetric parameter and conditional free degree parameter, the distribution of multivariate financial assets return is researched. Experimental results show that the proposed model can reasonably reflect the time-varying characteristics of the multivariate stock return distribution in China’s stock market.

Transfer Entropy Approach for Portfolio Optimization: An Empirical Approach for CESEE Markets

In this paper, we deal with the possibility of using econophysics concepts in dynamic portfolio optimization. The main idea of the research is that combining different methodological aspects in portfolio selection can enhance portfolio performance over time. Using data on CESEE stock market indices, we model the dynamics of entropy transfers from one return series to others. In the second step, the results are utilized in simulating the portfolio strategies that take into account the previous results. Here, the main results indicate that using entropy transfers in portfolio construction and rebalancing has the potential to achieve better portfolio value over time when compared to benchmark strategies.

Portfolio optimization for cointelated pairs: SDEs vs Machine learning

With the recent rise of Machine Learning (ML) as a candidate to partially replace classic Financial Mathematics (FM) methodologies, we investigate the performances of both in solving the problem of dynamic portfolio optimization in continuous-time, finite-horizon setting for a portfolio of two assets that are intertwined. In the Financial Mathematics approach we model the asset prices not via the common approaches used in pairs trading such as a high correlation or cointegration, but with the cointelation model in Mahdavi-Damghani (2013) that aims to reconcile both short-term risk and long-term equilibrium. We maximize the overall P&L with Financial Mathematics approach that dynamically switches between a mean-variance optimal strategy and a power utility maximizing strategy. We use a stochastic control formulation of the problem of power utility maximization and solve numerically the resulting HJB equation with the Deep Galerkin method introduced in Sirignano and Spiliopoulos (2018). We turn to Machine Learning for the same P&L maximization problem and use clustering analysis to devise bands, combined with in-band optimization. Although this approach is model agnostic, results obtained with data simulated from the same cointelation model gives a slight competitive advantage to the ML over the FM methodology1.

A deep Q-learning portfolio management framework for the cryptocurrency market

Deep reinforcement learning is gaining popularity in many different fields. An interesting sector is related to the definition of dynamic decision-making systems. A possible example is dynamic portfolio optimization, where an agent has to continuously reallocate an amount of fund into a number of different financial assets with the final goal of maximizing return and minimizing risk. In this work, a novel deep Q-learning portfolio management framework is proposed. The framework is composed by two elements: a set of local agents that learn assets behaviours and a global agent that describes the global reward function. The framework is tested on a crypto portfolio composed by four cryptocurrencies. Based on our results, the deep reinforcement portfolio management framework has proven to be a promising approach for dynamic portfolio optimization.