Analysis of Multivariate Chaotic Time Series using Neural Networks

With the advent of time series prediction in multidisciplinary domains, Multivariate Chaotic Time Series (MCTS) prediction has become a popular topic of re-search. Manifold applications like weather forecasting, stocks prediction, medical support, etc., deploy such kind prediction approach to predict the future of the time series based on past observations. In literature, various solutions have been explored and proposed to forecast future values in time series data. Significant efforts have been made to utilize various Neural Networks for time series prediction considering their applicability for future data prediction. However, a comprehensive evaluation of such existing methods is missing which demands attention for accurate and efficient prediction of time series data. In this paper, we have applied and evaluated various deep learning techniques on different dynamically generated data sets. Further, a comprehensive comparison of different techniques have been presented referencing loss observed with performance matrix Mean Absolute Error.