Search

Time series prediction has been widely applied to the finance industry in applications such as stock market price and commodity price forecasting. Machine learning methods have been widely used in financial time series prediction in recent years. How to label financial time series data to determine the prediction accuracy of machine learning models and subsequently determine final investment returns is a hot topic. Existing labeling methods of financial time series mainly label data by comparing the current data with those of a short time period in the future. However, financial time series data are typically non-linear with obvious short-term randomness. Therefore, these labeling methods have not captured the continuous trend features of financial time series data, leading to a difference between their labeling results and real market trends. In this paper, a new labeling method called "continuous trend labeling" is proposed to address the above problem. In the feature preprocessing stage, this paper proposed a new method that can avoid the problem of look-ahead bias in traditional data standardization or normalization processes. Then, a detailed logical explanation was given, the definition of continuous trend labeling was proposed and also an automatic labeling algorithm was given to extract the continuous trend features of financial time series data. Experiments on the Shanghai Composite Index and Shenzhen Component Index and some stocks of China showed that our labeling method is a much better state-of-the-art labeling method in terms of classification accuracy and some other classification evaluation metrics. The results of the paper also proved that deep learning models such as LSTM and GRU are more suitable for dealing with the prediction of financial time series data. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new cross-sample entropy, namely the composite multiscale partial cross-sample entropy (CMPCSE), for quantifying the intrinsic similarity of two time series affected by common external factors. First, in order to test the validity of CMPCSE, we apply it to three sets of artificial data. Experimental results show that CMPCSE can accurately measure the intrinsic cross-sample entropy of two simultaneously recorded time series by removing the effects from the third time series. Then CMPCSE is employed to investigate the partial cross-sample entropy of Shanghai securities composite index (SSEC) and Shenzhen Stock Exchange Component Index (SZSE) by eliminating the effect of Hang Seng Index (HSI). Compared with the composite multiscale cross-sample entropy, the results obtained by CMPCSE show that SSEC and SZSE have stronger similarity. We believe that CMPCSE is an effective tool to study intrinsic similarity of two time series. [ABSTRACT FROM AUTHOR]

How different are the emerging and the well-developed stock markets in terms of efficiency? To gain insights into this question, we compared an important emerging market, the Chinese stock market, and the largest and the most developed market, the US stock market. Specifically, we computed the Lempel–Ziv complexity (LZ) and the permutation entropy (PE) from two composite stock indices, the Shanghai stock exchange composite index (SSE) and the Dow Jones industrial average (DJIA), for both low-frequency (daily) and high-frequency (minute-to-minute)stock index data. We found that the US market is basically fully random and consistent with efficient market hypothesis (EMH), irrespective of whether low- or high-frequency stock index data are used. The Chinese market is also largely consistent with the EMH when low-frequency data are used. However, a completely different picture emerges when the high-frequency stock index data are used, irrespective of whether the LZ or PE is computed. In particular, the PE decreases substantially in two significant time windows, each encompassing a rapid market rise and then a few gigantic stock crashes. To gain further insights into the causes of the difference in the complexity changes in the two markets, we computed the Hurst parameter H from the high-frequency stock index data of the two markets and examined their temporal variations. We found that in stark contrast with the US market, whose H is always close to 1/2, which indicates fully random behavior, for the Chinese market, H deviates from 1/2 significantly for time scales up to about 10 min within a day, and varies systemically similar to the PE for time scales from about 10 min to a day. This opens the door for large-scale collective behavior to occur in the Chinese market, including herding behavior and large-scale manipulation as a result of inside information. [ABSTRACT FROM AUTHOR]