Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

作     者：Weisi Chen Walayat Hussain Francesco Cauteruccio Xu Zhang 

作者机构：School of Software EngineeringXiamen University of TechnologyXiamen361024China Peter Faber Business SchoolAustralian Catholic UniversityNorth Sydney2060Australia Department of Information EngineeringPolytechnic University of MarcheAncona60121Italy 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2024年第139卷第4期

页      面：187-224页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：funded by the Natural Science Foundation of Fujian Province,China (Grant No.2022J05291) Xiamen Scientific Research Funding for Overseas Chinese Scholars 

主　　题：Financial time series prediction convolutional neural network long short-term memory deep learning attention mechanism finance 

摘      要：Financial time series prediction,whether for classification or regression,has been a heated research topic over the last *** traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction ***,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and *** review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other *** illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related *** the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only *** remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency *** principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and t