Stock price movement prediction using combinative machine learning: A conceptual model

Abstract

Stock has dynamic characteristic and difficult to predict because its movement is affected by many factors. Various ways have been developed to predict stock price movements, including technical analysis and fundamental analysis. Besides these traditional techniques, there is also sentiment analysis. Many studies have tried to predict stock price movement through the machine learning approach using these various analysis techniques. However, the obtained results are vary depending on the object and variables used. This is because many factors influence stock price movements. These studies are presumed have not represented all existing factors. One of which is that no research considers the use of fundamental analysis in terms of currency exchange rates and stock prices index movements in other countries. Also, no studies consider the use of news in conducting sentiment analysis to predict stock price movements in Indonesia. This paper will describe a conceptual model that aims to predict stock price movements in Indonesia based on sentiment analysis, technical analysis, and fundamental analysis using machine learning approach.