Machine learning for liquidity prediction on Vietnamese stock market

As a critical consideration in investment decisions, stock liquidity has significance for all stakeholders in the market. It also has implications for the stock market's growth. Liquidity enables investors and issuers to meet their requirements regarding investment, financing or hedging, reducing investment costs and the cost of capital. The aim of this paper is to develop the machine learning models for liquidity prediction. The subject of research is the Vietnamese stock market, focusing on the recent years - from 2011 to 2019. Vietnamese stock market differs from developed markets and emerging markets. It is characterized by a limited number of transactions, which are also relatively small. The Multilayer Perceptron, Long-Short Term Memory and Linear Regression models have been developed. On the basis of the experimental results, it can be concluded that the LSTM model allows for prediction characterized by lowest value of MSE. The results of research can be used for developing the methods for decision support on stock markets. (C) 2021 The Authors. Published by Elsevier B.V.