Share Buyback Prediction using LSTM on Malaysian Stock Market

Abstract

Share buyback is a strategy for companies to repurchase their outstanding shares to reduce the number of shares from the open markets. With buyback, it indirectly increases the shares proportion and earning per shares (EPS) of a company. The aim of this study is to investigate the trend of share buyback strategy, and to design a simple prediction model for stock market price movement before initiating any buyback action. This study finds the use of Long Short-Term Memory (LSTM) as prediction algorithm has demonstrated that stock market price movement can be predicted using associated stock indicators, namely MACD and RSI which have an impact to the stock market price movement. The study also finds that the "Open" parameter based on the MAE, MSE and RMSE have been found to be the lowest value as compared to "High", "Low" and "Close" parameters.