Market-liquidity risk modeling and reinforcement machine learning algorithms under extreme market outlooks: applications to emerging markets

Abstract

This chapter examines the different aspects for the development of robust risk modeling techniques that attempt to address the problem of market-liquidity risk of multi-assets portfolios under extreme market outlooks, using reinforcement machine learning algorithms. The modeling algorithms and optimization techniques discussed in this chapter can aid in advancing risk and portfolio management practices in emerging markets, particularly in wake of the 2007-2009 financial crisis. Furthermore, the proposed risk management modeling techniques and optimization algorithms can have key applications in reinforcement machine learning, expert systems, smart financial functions, Internet of Things (IoT), and financial technology (FinTech) in big data ecosystems.