Anticipated learning method and system for short-term time series prediction

Abstract

The invention discloses an anticipated learning method and system for short-term time series prediction, solves the prediction problem of a short-term high-dimensional time series, and realizes accurate multi-step prediction of short-term high-dimensional data. According to the technical scheme, variables used for prediction are selected from time series data, predictive learning oriented to short-term time series prediction is conducted based on two trained neural network models, and finally the part, needing to be predicted, of the selected prediction variables is output.

Description

technical field [0001] The invention relates to the field of time series forecasting, in particular to a predictive learning method and system for short-term time series forecasting. Background technique [0002] Forecasting future values ​​of time series data is a challenging task, especially when only a few samples with high-dimensional variables are available. In fact, these data are considered unpredictable because there is little statistical information. However, such data are widely used in many fields (physics, economics, biology, medicine, etc.), so they place high demands on the accuracy and reliability of predictions. Any innovative advances in this area have broad implications. [0003] Existing time series forecasting methods, such as statistical methods such as ARIMA, robust regression, and exponential smoothing, and machine learning methods such as long and short memory networks, all require sufficiently long-term measured time series. However, due to the la...

AI Technical Summary

Problems solved by technology

However, due to the lack of information, there is no effective method for forecasting short-term time series

In addition, short-term high-dimensional time series have received more and more attention in various fields, but the forecasting of short-term high-dimensional time series has been rarely studied

Images