To improve the prediction effect of time series, we make a systematic study of various time series prediction methods based on statistics and machine learning in this paper. In the experiment, we compare the prediction results of several prediction methods. In particular, much research has been done on the selection of experimental data because representative time series data can better test the effectiveness and practicability of the prediction method. Based on the idea of divide and conquer of complex problems and the strategy of continuous optimization of machine learning, we proposed the prediction methods of LSTM-TFE, LR-TFE, and BR-TFE combined the EEMD, LSTM, LR, and BR methods in this paper. These methods use EEMD to decompose complex time series into several relatively milder, more regular and stable subsequences. Then the prediction model of each subsequence based on machine learning is carried out by using the LSTM, LR, or BR methods. We use these prediction models to predict the value of each subsequence. Finally, the value of multiple subsequences is fused to form the prediction results of the original complex time series. To verify the proposed method comprehensively, we select three representative time series data to test this paper. From the experimental results, we found that the proposed method has a good effect. INDEX TERMS LSTM, short-term forecasting, EEMD, price prediction, time series.

No abstract

No abstract

The stock market is a chaotic, complex, and dynamic financial market. The prediction of future stock prices is a concern and controversial research issue for researchers. More and more analysis and prediction methods are proposed by researchers. We proposed a hybrid method for the prediction of future stock prices using LSTM and ensemble EMD in this paper. We use comprehensive EMD to decompose the complex original stock price time series into several subsequences which are smoother, more regular and stable than the original time series. Then, we use the LSTM method to train and predict each subsequence. Finally, we obtained the prediction values of the original stock price time series by fused the prediction values of several subsequences. In the experiment, we selected five data to fully test the performance of the method. The comparison results with the other four prediction methods show that the predicted values show higher accuracy. The hybrid prediction method we proposed is effective and accurate in future stock price prediction. Hence, the hybrid prediction method has practical application and reference value.

In recent years, with the rapid development of wind power generation, some problems are gradually highlighted. At present, one of the essential methods to solve these problems is to predict wind speed. In this paper, a hybrid BRR-EEMD method is proposed for short-term wind speed prediction based on the Bayesian ridge regression prediction method and ensemble empirical mode decomposition. We use ensemble empirical mode decomposition of the hybrid method to decompose complex time series of wind speed into several relatively milder, more regular, and stable subsequences. Then each subsequence is carried out by using the Bayesian ridge regression method. The value of each subsequence is predicted by it. Finally, the value of multiple subsequences is fused to form the prediction results of the original complex time series of wind speed. In order to verify the proposed method comprehensively, this paper selects two data to test. According to the results, predicted values have shown higher accuracy compared with the various prediction methods. Therefore, the hybrid BRR-EEMD method is accurate and effective in predicting wind speed, which has practical significance and potential value. INDEX TERMS Ensemble empirical mode decomposition, short-term predicting, Bayesian ridge regression, wind speed, time series.

This paper introduces a multiscale multifractal multiproperty analysis based on Rényi entropy (3MPAR) method to analyze short-range and long-range characteristics of financial time series, and then applies this method to the five time series of five properties in four stock indices. Combining the two analysis techniques of Rényi entropy and multifractal detrended fluctuation analysis (MFDFA), the 3MPAR method focuses on the curves of Rényi entropy and generalized Hurst exponent of five properties of four stock time series, which allows us to study more universal and subtle fluctuation characteristics of financial time series. By analyzing the curves of the Rényi entropy and the profiles of the logarithm distribution of MFDFA of five properties of four stock indices, the 3MPAR method shows some fluctuation characteristics of the financial time series and the stock markets. Then, it also shows a richer information of the financial time series by comparing the profile of five properties of four stock indices. In this paper, we not only focus on the multifractality of time series but also the fluctuation characteristics of the financial time series and subtle differences in the time series of different properties. We find that financial time series is far more complex than reported in some research works using one property of time series.

In general, the stock trend is mainly driven by the big order transactions. Believing that the stock rise with a large volume is closely associated with the big order net inflow, we propose an efficient stock recommendation model based on big order net inflow in the paper. In order to compute the big order net inflow of stock, we use the M/G/1 queue system to measure all tick-by-tick transaction data. Based on an indicator of the big order net inflow of stock, we select some stocks with the higher value of the net inflow to constitute the prerecommended stock set for the target investor user. In order to recommend some stocks with which this style is familiar them to the target users, we divide lots of investors into several categories using fuzzy clustering method and we should do our best to choose stocks from the stock set once operated by those investors who are in the same category with the target user. The experiment results show that the recommended stocks have better gains during the several days after the recommended stock day and the proposed model can provide reliable investment guidance for the target investors and let them get more stock returns.

No abstract