A Tool based on ML-driven Graphical Model for Stock Price Prediction by Leading Indicators

Abstract

Abstract Stock prediction has become an emerging issue in recent decades and many studies have incorporated it with social systems to provide a better accuracy for the prediction results. Machine learning (ML) model is widely studied and developed to show better performance in data analytics and prediction, which can be also applied in the stock markets for the price prediction.To be better applied in the stock market for price predication, it is necessary to finalize a ML-driven toolbox that can be easily adopted into the stock market. In this paper, aiming at the task of time series (financial) feature extraction and prediction of price movements, a new convolutional novel neural network to improve the prediction accuracy of stock trading is proposed. The proposed model is called SSACNN, short form of stock sequence array convolutional neural network that collects data including historical data of prices and its leading indicators (options / futures) for a stock to take an array as the input graph of CNN framework. In our experimental results, the motion prediction performance of SSACNN has been improved significantly and proved that it has the potential to be applied in the real financial market.