Stock Price Trends Prediction Based on the Classical Models with Key Information Fusion of Ontologies

Abstract

An ontology of the financial field can support effective association and integration of financial knowledge. Based on behavioral finance, social media is increasingly applied as one of the data sources for information fusion in stock forecasting to approximate the patterns of market changes. By predicting Tesla (TSLA) stock price trends, this study finds that satisfactory forecasting results can be achieved using classical models and incorporating key information features from the technical indicator ontology class and the investor behavior ontology class, even in the face of the impact of the COVID-19 epidemic. In the post-epidemic period, the back propagation neural network (BPNN) model is used to predict the price trend of TSLA for the next five trading days with an accuracy of up to 91.34%, an F1 score of 0.91, and a return of up to 268.42% obtained from simulated trading. This study extends the research on stock forecasting using fused information in the ontology of the financial field, providing a new basis for general investors in the selection of fusion information and the application of trading strategies and providing effective support for organizations to make intelligent financial decisions under uncertainty.