Research on Quantitative Investment Strategies Based on Deep Learning Algorithms in the Context of the Need for Information Management

Abstract

The rapid development of the contemporary financial sector relies on the support of information technology. For the financial sector, effective management of investment information and intelligent decision-making can achieve a significant increase in yield to a certain extent. With the advent of the era of big data on the Internet, the competition among investment companies has become more and more intense, and how to achieve effective management of financial information through artificial intelligence technology, and then make quantitative investment from manual to intelligent, has gradually become the focus of asset management companies. In this paper, we introduce kernel principal component analysis (KPCA) to extract stock trend feature information and assist corresponding stock indicators to construct feature vectors, and then use quantum particle swarm (QPSO) algorithm improved long and short term memory (LSTM) neural network to make trend prediction based on features, and formulate stop-earnings and stop-loss strategies for prediction results. The experimental results show that the quantitative investment method proposed in this paper can achieve higher investment returns compared with other methods, and can effectively adapt to the information management needs of investment companies and help improve the management level of enterprises.