Liquidity prediction on Vietnamese stock market using deep learning

Abstract

Abstract Machine-learning methods have recently been successfully used in different areas, but there are also many fields where such studies have not been carried out. One of them is advanced issue regarding liquidity prediction and forecasting of financial time series. It is a very challenging task because this sphere is highly volatile and dynamic, especially if we consider emerging stock markets like the Vietnamese one. The authors proposed deep learning as the most modern technique to forecast the future directions of an emerging stock market and developed a predictive model to forecast liquidity for such a market. A fully-connected neural network based on Multilayer Perceptron (MLP), Mixed Deep Learning (MDL), and Linear Regression (LR) was tested. The following metrics were used: mean absolute error (MAE) and mean square error (MSE), and the best values of MSE in the MDL model were achieved. Based on the proposed model, which is the main contribution of the paper, better investment decisions can be achieved. The authors’ solution is dedicated to and empirically verified on the Vietnamese stock market, so future works should extend the model to other ones, emerging and developed alike.