Can we predict the unpredictable?

Abstract

Time series forecasting is of fundamental importance for a variety of domains including the prediction of earthquakes, financial market prediction, and the prediction of epileptic seizures. We present an original approach that brings a novel perspective to the field of long-term time series forecasting. Nonlinear properties of a time series are evaluated and used for long-term predictions. We used financial time series, medical time series and climate time series to evaluate our method. The results we obtained show that the long-term prediction of complex nonlinear time series is no longer unrealistic. The new method has the ability to predict the long-term evolutionary trend of stock market time series, and it attained an accuracy level with 100% sensitivity and specificity for the prediction of epileptic seizures up to 17 minutes in advance based on data from 21 epileptic patients. Our new method also predicted the trend of increasing global temperature in the last 30 years with a high level of accuracy. Thus, our method for making long-term time series predictions is vastly superior to existing methods. We therefore believe that our proposed method has the potential to be applied to many other domains to generate accurate and useful long-term predictions.

<p>Secular Seasonality and Trend Forecasting of Tuberculosis Incidence Rate in China Using the Advanced Error-Trend-Seasonal Framework</p>

“…In addition, it should be noted that the Lee-Carter and GenericPred methods are recently shown to be helpful in examining the long-term epidemic behaviors of diseases incidence. 11,28 Thus, future researches are expected to make comparison about their long-term forecasting performances between the ETS framework and the above-mentioned methods. Another worth noting is that there may be underprojection or overprojection during the process of ETS model development, which may have an effect on its generalization ability of this model.…”

“…There is an abundance of computational models used to simulate and forecast time series in various research domains, such as business, environmental engineering, finance and economy, and medicine, etc., [9][10][11] yet most of them focused on a short-term forecasting. Such a predictive period may provide limited clues for the process of the decision-making in applications.…”

Epidemiological analysis of hemorrhagic fever with renal syndrome in China with the seasonal-trend decomposition method and the exponential smoothing model

“…Obtaining the original data series through the reported data, and analyzing the spatial-temporal characteristics through the time series analysis method is an important method to analyze the time data in the epidemiology, which can effectively obtain the important characteristics of data variation, such as periodicity and seasonality22; in addition, the short-term and long-term forecast can evaluate the control measures, in the meantime, it can adopts effective and timely solutions for the epidemic peak that may occur or the reappeared prevalence or outbreak26. Some scholars analyze the annual reported data of HFRS in China through time series model like ARMA, analyze the variation trends, seasonal trends and epidemic characteristics of the annual data of HFRS, and verify the effectiveness of the model2728.…”

Time series analysis of temporal trends in the pertussis incidence in Mainland China from 2005 to 2016

“…Since ETS model and ARIMA model have become more popular in time series in recent years as mentioned above912, in this study, the two were implemented as the epidemiological analysis methods.…”