Systematic Market and Asset Liquidity Risk Processes for Machine Learning: Robust Modeling Algorithms for Multiple-Assets Portfolios

Abstract

This chapter presents contemporary machine learning techniques for the computation of market and asset liquidity risk for multiple-assets portfolios. Furthermore, this research focuses on the theoretical aspects of asset liquidity risk and presents two critically robust machine learning processes to measuring the market liquidity risk for trading securities as well as for asset management objectives. To that end, this chapter extends research literature related to the computation of market and asset liquidity risks by providing generalized theoretical modeling algorithms that can assess both market and liquidity risks and integrate both risks into multiple-assets portfolio settings. The robust modeling algorithms can have practical applications for multiple-securities portfolios and can have many uses and application in financial markets, particularly in light of the 2007–2009 global financial meltdown in issues related to machine learning for the policymaking process and machine learning techniques for the Internet of Things (IoT) data analytics. In addition, risk assessment algorithms can aid in advancing risk management practices and have important applications for financial technology (FinTech), artificial intelligence, and machine learning in big data environments.