An analytical review for event prediction system on time series

Abstract

Listen

Translate article

This Time series mining is a new area of research in temporal databases and has been an active area of research with its notable recent progress. Event prediction is one of the main goals of time series mining which have important roles for appropriate decision making in different application area. So far, different studies have been presented in the field of time series mining for meaningful events prediction, which have ample challenges. Lack of systematic identification of challenges causes some obstacles for the development of methods. In this paper, due to the abundance and diversity of challenges in event prediction system on time series, lack of a perfect platform for their systematic identification and removing barriers for the development of methods, a classification is proposed for challenging problems of event prediction system on time series. Also, reviewed and analyzed the application of data mining techniques for solving different challenges in event prediction system on time series. For this goal, the article tries to closely study and categorize related researches for better understanding and to reach a comparison structure that can map data mining techniques into the event prediction challenges. The proposed classification of this paper by introducing systematic challenges can help create different research pivots for the elimination of challenges in different areas of applying and developing methods. We think that this paper can help researchers in event prediction systems on time series for the future activities.