Integrating technical indicators, chip factors and stock news for enhanced stock price predictions: A multi-kernel approach

In the field of stock price forecasting, we are actively seeking to integrate various information to more accurately grasp market dynamics. Although historical stock prices and financial news have been widely used in previous studies, it is relatively rare to find research considering news-based, technical, and chip factors simultaneously and evaluating their combined effect. In this study, we innovatively propose a multi-kernel model that not only combines news-based, technical, and chip factor analysis but also utilizes market data provided by the Taiwan Stock Exchange, including institutional trading situations and stock price technical indicators. The aim is to further enhance the prediction accuracy of stock price dynamics. Based on the frequency of word occurrences, we design a new discriminant index to extract features highly correlated with stock prices from financial news. The empirical results show that our multi-kernel model significantly surpasses the single-kernel model in prediction accuracy. However, we also find that although financial news is somewhat correlated with stock price dynamics, information such as chip factors and stock price technical indicators contribute more significantly in our model. This further validates that our multi-kernel learning algorithm can effectively handle multifaceted data sources and give appropriate weights according to the importance of each data point, thereby enhancing the comprehensiveness of prediction. Through this research, we hope to bring new perspectives and inspirations to the field of stock price forecasting.