Research on financial assets transaction prediction model based on LSTM neural network
- PDF / 1,717,708 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 225 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Research on financial assets transaction prediction model based on LSTM neural network Xue Yan1 • Wang Weihan2 • Miao Chang1 Received: 30 January 2020 / Accepted: 2 May 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In recent years, with the breakthrough of big data and deep learning technology in various fields, many scholars have begun to study the stock market time series by using deep learning technology. In the process of model training, the selection of training samples, model structure and optimization methods are often subjective. Therefore, studying these influencing factors is beneficial to provide scientific suggestions for the training of recurrent neural networks and is beneficial to improve the prediction accuracy of the model. In this paper, the LSTM deep neural network is used to model and predict the financial transaction data of Shanghai, and the three types of factors affecting the prediction accuracy of the model are systematically studied. Finally, a high-precision short-term prediction model of financial market time series based on LSTM deep neural network is constructed. In addition, this paper compares BP neural network, traditional RNN and RNN improved LSTM deep neural network. It proves that the LSTM deep neural network has higher prediction accuracy and can effectively predict the stock market time series. Keywords LSTM Financial model Transaction forecasting Model analysis Financial market
1 Introduction Since the mid-19th century, the limited liability company system has gradually been replaced by joint-stock companies. The degree of prosperity of financial transactions represents the economic status of a country. According to statistics, the total market capitalization of China’s stock market in 2015 has reached 146% of GDP, ranking first among developing countries. Moreover, in 2015, the total market capitalization of the US stock market accounted for 174% of GDP, leading the developed countries. The stock market, as a high-risk investment market with both risks and returns, has been closely watched by investors. Stock exchanges in various countries generate huge amounts of transaction data every day. Investors and investment & Wang Weihan [email protected] 1
School of Management, Heilongjiang University of Science and Technology, Harbin 150022, Heilongjiang, China
2
School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai 200433, China
institutions are increasingly using data as their primary reference when trading securities and investing in stocks. Real-time transaction data, such as K-line and time sharing, are often an objective reflection of the market. Investors and investment institutions often select these historical data for analysis and forecasting in order to achieve higher profits [1]. In an attempt to predict the changing trend of financial prices, financial investors are constantly observing the subtle
Data Loading...
