The purpose of this study is to develop portfolio optimization and assets allocation using our proposed models. The study is based on a non-parametric efficiency analysis tool, namely Data Envelopment Analysis (DEA). Conventional DEA models assume non-negative data for inputs and outputs. However, many of these data take the negative value, therefore we propose the MeanSharp-βRisk (MShβR) model...

This paper considers the asset allocation strategies for members of defined-contribution pension plans with exponential utility when there are three types of asset, cash, bonds and stocks. The portfolio problem is to maximize the expected utility of terminal wealth that uses the plan member’s final wage as a numeraire, in the presence of three risk sources, interest risk, asset risk and wage ri...

Over the decades, Markowitz framework has been used extensively in portfolio analysis though it puts too much emphasis on of market uncertainty rather than trend prediction. While generative adversarial network (GAN) and conditional GAN (CGAN) have explored to generate financial time series extract features that can help analysis. The limitation CGAN stands putting generating keeping this gener...

In this paper, we examine the impact of including environmental, social and governance (ESG) criteria in allocation equity portfolios. We focus on risk return characteristics resulting ESG portfolios investment strategies. Two specific measures are considered to quantify performance a company; rating greenhouse gas (GHG) emission intensity. For both measures, carry out empirical portfolio analy...

Deep reinforcement learning (DRL) has reached an unprecedent level on complex tasks like game solving (Go [], StarCraft II []), and autonomous driving. However, applications to real financial assets are still largely unexplored it remains open question whether DRL can reach super human level. In this demo, we showcase state-of-the-art methods for selecting portfolios according environment, with...