دانلود رایگان مقاله انگلیسی EMD2FNN: تقسیم حالت تجربی و ماشین فاکتورگیری مبتنی بر شبکه عصبی برای پیش بینی روند بازار سهام - الزویر 2019

Abstract

Stock market forecasting is a vital component of financial systems. However, the stock prices are highly noisy and non-stationary due to the fact that stock markets are affected by a variety of factors. Predicting stock market trend is usually subject to big challenges. The goal of this paper is to introduce a new hybrid, endto-end approach containing two stages, the Empirical Mode Decomposition and Factorization Machine based Neural Network (EMD2FNN), to predict the stock market trend. To illustrate the method, we apply EMD2FNN to predict the daily closing prices from the Shanghai Stock Exchange Composite (SSEC) index, the National Association of Securities Dealers Automated Quotations (NASDAQ) index and the Standard & Poor’s 500 Composite Stock Price Index (S&P 500), which respectively exhibit oscillatory, upward and downward patterns. The results are compared with predictions obtained by other methods, including the neural network (NN) model, the factorization machine based neural network (FNN) model, the empirical mode decomposition based neural network (EMD2NN) model and the wavelet de-noising-based back propagation (WDBP) neural network model. Under the same conditions, the experiments indicate that the proposed methods perform better than the other ones according to the metrics of Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Furthermore, we compute the profitability with a simple long-short trading strategy to examine the trading performance of our models in the metrics of Average Annual Return (AAR), Maximum Drawdown (MD), Sharpe Ratio (SR) and AAR/MD. The performances in two different scenarios, when taking or not taking the transaction cost into consideration, are found economically significant.

5. Concluding Remarks

This paper introduces a novel method for predicting the stock prices by integrating EMD, FM and the neural 400 network together. EMD is used to decompose the original nonlinear and non-stationary time series into IMFs that can be considered quasi-stationary. The produced IMFs are used as inputs to the neural network, which incorporates the FM strategy to exploit the nonlinear interactions between features extracted at different time scales. The resulting EMD2FNN can handle not only the nonlinearity but also the influence among time scales, which are two aspects that the existing methods face challenges. The numerical experiments demonstrated that 405 the integrated methods have significant advantages in improving the prediction accuracies, measured by MAE, RMSE and MAPE. Furthermore, the profitability is computed with a simple long-short trading strategy to examine the trading performance of the proposed models by taking transaction cost into account or not. The performances, measured by AAR, MD, SR and AAR/MD, are also found economically significant. This study is another example that demonstrates the power of combining EMD with neural network to achieve 410 outstanding performance in stock price predictions. In fact, we believe that EMD can be used in conjunction with other statistic or artificial intelligent strategies to form general methods for predicting, especially for the time series that is nonlinear and non-stationary in nature. Various combinations in algorithm design can be investigated in the future to tackle problems emerging from different applications.