Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
A Long Short-Term Memory Network Stock Price Prediction with Leading Indicators
Big Data ( IF 2.6 ) Pub Date : 2021-10-14 , DOI: 10.1089/big.2020.0391 Jimmy Ming-Tai Wu, Lingyun Sun, Gautam Srivastava, Jerry Chun-Wei Lin
Big Data ( IF 2.6 ) Pub Date : 2021-10-14 , DOI: 10.1089/big.2020.0391 Jimmy Ming-Tai Wu, Lingyun Sun, Gautam Srivastava, Jerry Chun-Wei Lin
The accuracy of the prediction of stock price fluctuations is crucial for investors, and it helps investors manage funds better when formulating trading strategies. Using forecasting tools to get a predicted value that is closer to the actual value from a given financial data set has always been a major goal of financial researchers and a problem. In recent years, people have paid particular attention to stocks, and gradually used various tools to predict stock prices. There is more than one factor that affects financial trends, and people need to consider it from all aspects, so research on stock price fluctuations has also become extremely difficult. This paper mainly studies the impact of leading indicators on the stock market. The framework used in this article is proposed based on long short-term memory (LSTM). In this study, leading indicators that affect stock market volatility are added, and the proposed framework is thus named as a stock tending prediction framework based on LSTM with leading indicators (LSTMLI). This study uses stock markets in the United States and Taiwan, respectively, with historical data, futures, and options as data sets to predict stock prices in these two markets. We measure the predictive performance of LSTMLI relative to other neural network models, and the impact of leading indicators on stock prices is studied. Besides, when using LSTMLI to predict the rise and fall of stock prices in the article, the conventional regression method is not used, but the classification method is used, which can give a qualitative output based on the data set. The experimental results show that the LSTMLI model using the classification method can effectively reduce the prediction error. Also, the data set with leading indicators is better than the prediction results of the single historical data using the LSTMLI model.
更新日期：2021-10-20
京公网安备 11010802027423号