Applied Sciences, Vol. 13, Pages 12160: Advancing Financial Forecasts: A Deep Dive into Memory Attention and Long-Distance Loss in Stock Price Predictions

Applied Sciences, Vol. 13, Pages 12160: Advancing Financial Forecasts: A Deep Dive into Memory Attention and Long-Distance Loss in Stock Price Predictions

Applied Sciences doi: 10.3390/app132212160

Authors: Shijie Yang Yining Ding Boyu Xie Yingyi Guo Xinyao Bai Jundong Qian Yunxuan Gao Wuxiong Wang Jinzheng Ren

In the context of the rapid evolution of financial markets, the precise prediction of stock prices has become increasingly complex and challenging, influenced by a myriad of factors including macroeconomic indicators, company financial conditions, and market sentiment. A model integrating modern machine learning techniques has been introduced in this study, aimed at enhancing the accuracy of stock price prediction. To more effectively capture long-term dependencies in time series data, a novel memory attention module has been innovatively integrated and a unique long-distance loss function has been designed. Through a series of experimental validations, the effectiveness and superiority of this model in the realm of stock price prediction have been demonstrated, especially evident in the R2 evaluation metric, where an impressive score of 0.97 has been achieved. Furthermore, the purpose, methodology, data sources, and key results of this research have been elaborately detailed, aiming to provide fresh perspectives and tools for the field of stock price prediction and lay a solid foundation for future related studies. Overall, this research has not only enhanced the accuracy of stock price prediction but also made innovative contributions in terms of methodology and practical applications, bringing new thoughts and possibilities to the domain of financial analysis and prediction.