Method and apparatus for performing time series forecasting through machine learning

Abstract

The invention relates to a method and apparatus for performing time series forecasting through machine learning. The method herein includes the following steps: pre-processing the acquired time series data, and obtaining a result of the pre-processing; on the basis of the result of pre-processing, detecting whether the time series data contains seasonal cycles; if the result of the pre-processing determines that the time series data contains the seasonable cycles, in accordance with the Akaike information criterion and bayesian information criterion, selecting a time series model; if the result of the pre-processing determines that the time series data does not contain seasonable cycles, adding the time series data to a time series data pool, and if the number of the added time series data is greater than a preset threshold value, returning to the step of selecting a time series model based on the Akaike information criterion and bayesian information criterion. According to the invention, the method herein has the beneficial advantages that the method uses automation procedures to complete time series prediction, continues the optimization of models by means of machine learning, and increases prediction accuracy.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of information processing, and in particular, to a method and device for time series prediction through machine learning. Background technique [0002] Time series predictive analysis technology has important application value in many fields such as science and technology and economy. Scientifically and correctly predicting and analyzing various actual time series can produce huge economic and social benefits. Due to the complex nonlinear characteristics of the actual system, the linear and nonlinear models used in the early time series analysis have certain limitations in theoretical analysis and practical application. [0003] With the advancement of IT (Information Technology) technology, people's ability to use information technology to generate and collect data has greatly improved. Tens of millions of databases are used in business management, government offices, scientific rese...

AI Technical Summary

Problems solved by technology

[0004] At present, the industry mainly uses the triple exponential smoothing (Triple / Three Order Exponential Smoothing, Holt-Winters) algorithm after manually determining the trend and seasonality of the time series. This algorithm is based on the primary exponential smoothing and the secondary exponential smoothing algorithms. However, This kind of manual analysis completes the timing prediction process is cumbersome, and parameters need to be adjusted repeatedly according to the data, and the prediction results are prone to deviations. As a result, large-scale IT environments can only make timing predictions for a small number of key KPIs. At present, there is no method that can completely solve the above problems or device appears

Images