Research And Implementation Of Intelligent Financial Asset Management System Based On Deep Learning

The success of deep learning in various fields has prompted researchers to combine artificial intelligence algorithms with financial investments,using deep learning algorithms to intelligently evaluate users' investment behaviour and make their decisions smarter.At the same time,the increasing volume of data in the financial market has led to higher demands on the processing capabilities of financial analytics platforms,from data collection,processing and analysis to ensure efficiency and accuracy.Therefore,improving the performance of financial data analytics platforms is a key issue to be addressed today.There is a growing number of research and applications of financial data analytics platforms,the market is uneven and there is still a high barrier to entry for the average user.In this paper,we use deep reinforcement learning-based algorithms to experimentally explore problems related to stock price prediction,portfolio and algorithmic trading,and analyse both model performance and algorithmic output through comparative experiments.Meanwhile,for the construction of a financial data analysis platform,this paper uses the more popular Kubernetes container orchestration and microservices technology to build a distributed financial data analysis system.The main contributions of this paper are as follows.(1)Introducing deep reinforcement learning into the financial market,using the powerful fitting and representation capabilities of deep reinforcement learning to provide a solution to the problem of difficult to grasp non-linear data in finance.(2)A financial asset management method is proposed to precisely find the appropriate trading point in a changing trend and trade it automatically through the analysis and intelligent combination of stock trading data,so as to improve investors' returns under the premise of controlled risk.(3)An intelligent financial asset management system is designed,which is built based on Kubernetes and microservices,and can achieve real-time analysis of financial data with high concurrency and high performance,and deep reinforcement learning with efficient and usable functions,which can help users observe the changes of financial market trends and make reasonable suggestions to their investment decisions at the same time.