A Smart and Dynamic Decision Support System for Nonlinear Environments

Abstract

The design of a dynamic and efficient decision-making system for real-world systems is an essential but challenging task since they are nonlinear, chaotic, and high dimensional in nature. Hence, a Support Vector Machine (SVM)-based model is proposed to predict the future event of nonlinear time series environments. This model is a non-parametric model that uses the inherent structure of the data for forecasting. The dimensionality of the data is reduced besides controlling noise as the first preprocessing step using the Hybrid Dimensionality Reduction (HDR) and Extended Hybrid Dimensionality Reduction (EHDR) nonlinear time series representation techniques. It is also used for subsequencing the nonlinear time series data. The proposed SVM-based model using EHDR is compared with the models using Symbolic Aggregate approXimation (SAX), HDR, SVM using Kernel Principal Component Analysis (KPCA), and SVM using varying tube size values for historical data on different financial instruments. A comparison of the experimental results of the proposed model with other models taken for the experimentation has proven that the prediction accuracy of the proposed model is outstanding.