Prediction of Shanghai Stock Exchange Composite Index Based on a Deep Convolutional Fuzzy System
Download as PDF
DOI: 10.23977/GEBM2020.011
Author(s)
Li Xinyan, Zuo Yifan, and Sun Shitao
Corresponding Author
Li Xinyan
ABSTRACT
Artificial intelligence has brought new ideas to the field of programmatic transactions in financial sector. Compared to factor analysis with historical data, models of artificial intelligence are more comprehensive and accurate. A deep convolutional fuzzy system with fast training algorithm is an effective model that can be used to predict the index of stock market. This model is a multi-layered structure containing many levels of fuzzy systems. Due to its high efficiency and accuracy, the system with fast training algorithm was quite successful in predicting Shanghai Stock Exchange (SSE) Composite Index. Past daily returns of stocks are also used in the strategy. Annualized rate of return, maximum drawdown rate, Sharpe ratio and information ratio are used to evaluate the application of this model. The deep convolutional fuzzy system with the training algorithm can predict not only the cost of stock and the index of both domestic and foreign stock, but also the index of digital currency such as bitcoin.
KEYWORDS
Shanghai Stock Exchange Composite index, Convolutional Neural Networks, Fuzzy System, Quantitative investment