Energy Transition, Asset Price Fluctuations, and Dynamic Portfolio Decisions

Portfolio selection is an important yet challenging task in AI for FinTech. One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions. The existing methods, however, fall short of capturing: 1) the complicated sequential patterns for asset price series and 2) the price correlations among multiple assets. In this paper, under a deep reinforcement learning paradigm for portfolio selection, we propose a novel Relation-aware Transformer (RAT) to handle these aspects. Specifically, being equipped with our newly developed attention modules, RAT is structurally innovated to capture both sequential patterns and asset correlations for portfolio selection. Based on the extracted sequential features, RAT is able to make profitable portfolio decisions regarding each asset via a newly devised leverage operation. Extensive experiments on real-world crypto-currency and stock datasets verify the state-of-the-art performance of RAT.

Download Full-text

Dynamic Portfolio Selection

Alternative Decision-Making Models for Financial Portfolio Management - Advances in Finance, Accounting, and Economics ◽

10.4018/978-1-5225-3259-0.ch005 ◽

2017 ◽

pp. 116-140

Keyword(s):

Portfolio Optimization ◽

Asset Allocation ◽

Piecewise Linear ◽

Relevant Literature ◽

Asset Price ◽

Piecewise Linear Function ◽

Simple Formulation ◽

Wolfram Mathematica ◽

Dynamic Portfolio ◽

Algorithmic Construction

In this chapter I recognize the importance of the stochastic programming as a significant tool in financial planning. The current practice of portfolio optimization is still limited to the simple formulation of linear programming (LR) or quadratic programming (QR) type. For that reason, relevant literature on asset-liability management (ALM) model has been reviewed and two different ALM approaches are compared: first piecewise linear function; and second a nonlinear utility function. This chapter shows that the mathematical programming methodology is ready to challenge the huge problem arising from LP portfolio optimization. A special emphasis was put on the shape of the investors' payoff functions in asset price equilibrium. The results underpin our claim that the nonlinear ALM model generated better asset allocation. An algorithmic construction of ALM model is developed in Wolfram Mathematica 9.

Download Full-text