Optimum and Coherent Economic Capital Forecasts with Reinforcement Machine Learning: Evidence from Optimization Algorithms under Long and Short-Sales Multiple Asset Portfolios of Emerging Markets

This chapter extends research literature associated with modern portfolio risk management techniques, by presenting robust modeling algorithms for nonlinear dynamic asset allocation and management under extreme events of illiquidity and adverse market perspectives. This research study examines, from portfolio managers’ perspective, the performance of liquidity-adjusted risk modeling in obtaining optimum and coherent economic capital structures, subject to the application of meaningful operational and financial constraints. Specifically, this chapter examines robust quantitative modeling methods to optimum economic capital allocation, in a liquidity-adjusted value at risk (L-VaR) framework, particularly from the perspective of trading portfolios that have both long and short-sales trading positions. The empirical results, of emerging Gulf Cooperation Council (GCC) financial markets, strongly confirm the importance of enforcing financially and operationally meaningful nonlinear and dynamic constraints, when they are available, on the L-VaR optimization procedure. The implemented optimization techniques and risk assessment algorithms can aid in advancing risk management practices in emerging markets, particularly in the wake of the 2007–2009 financial turmoil. Furthermore, the proposed risk management technique and optimization algorithms can have important applications for financial technology (FinTech) and reinforcement machine learning in big data environments.