Predicting the Future Using Web Knowledge: State of the Art Survey A. Mosavi1, Y. Bathla1, A. Varkonyi-Koczy 1,2 1 Institute
of Automation, Kando Kalman Faculty of Electrical Engineering, Obuda University, 1431 Budapest, Hungary 2 Department of Mathematics and Informatics, J. Selye University, 945 01 Komarno, Slovakia {amir.mosavi, yatish.bathla, koczy.annamaria}@kvk.uni-obuda.hu
Abstract. Accurate prediction models can potentially transform businesses, organizations, governments, and industries. Data-driven prediction methods and applications have recently become very popular. One of the novel method of building prediction models is to use data-driven methods and knowledge discovery on the web contents. This includes the news and media as well as social networks contents. This method uses advanced technologies of big data, machine learning, deep learning and intelligent optimization for finding patterns in big data to build prediction models. This article presents a state of the art survey on the latest technological advancements, novel methods, and applications in developing prediction models. Keywords: Predictive Analytics, Predictive Decision Models, Web Dynamics
1
Introduction
An intelligent agent in a complex environment of numerous intelligent agents is often concerned with the future changes to its environment [1]. As Kira et al. [2] describes, the potential changes may partly be the consequences of its own actions, and partly due to the various chains of the events caused by the actions of other agents situated in the same environment. Scientific prediction would be the way to study and analyze the future events [3]. Due to the limited perceptive capabilities of intelligent agents building the prediction models in the complex environments is considered as a highly demanding task. However the rapid reproduction of the World Wide Web and, internet of things (IoT) [3,4] is changing all that. Today people as the intelligent agents in the virtual world of the Web are changing the current state of the world [4,5]. Consequently, today the perceptive capabilities of intelligent agents have been highly improved by the expansion of the IoT, e.g. Web pages, increasing the sources of textual information, news reports, Wikipedia pages, tweets, search inquiries, organizing, and generating information. This would lead to build better predictive models for providing knowledge on likelihoods of future events and actionable forecasts [5]. This paper is concerned
A. Mosavi, Y. Bathla, A. Varkonyi-Koczy, Predicting the Future Using Web Knowledge: State of the Art Survey, Recent Advances in Technology Research and Education, Springer Nature (2017).