Natural visibility encoding for time series and its application in stock trend prediction

As a newly developed method, the natural visibility graph (NVG) has attracted great attention. Most of the previous research focuses on exploring the time series using the NVG from the angle of the complex network while few efforts have been paid to the degree sequence of the NVG. Recently, two studies indicate that the degree sequence of the horizontal visibility graph (HVG) represents the local motif information of the time series and utilize it to classify time series. Though the performance of the HVG-based classification algorithm is not satisfying, we would like to further explore whether the degree sequence of the NVG could be utilized in practical applications. Hence, we propose the concept of natural visibility encoding for the time series to extract the motif information from the time series through the NVG transformation. To obtain the local motif information from the whole time series, a moving window encoding strategy is also developed. The stock trend prediction (STP) problem is selected as the application area and a universal STP framework is proposed based on the natural visibility encoding and the moving window strategy. By conducting three experiments with over twenty baseline algorithms and the ablation study, the validation, effectiveness, and robustness of the proposed framework are proven. The success of the proposed framework suggests that the degree sequence of the NVG transformation could provide useful information for practical usage. We hope our work could inspire further efforts on investigating the degree sequence of the NVG transformation in the dimension of time. (C) 2021 Elsevier B.V. All rights reserved.