A nonlinear time-series prediction methodology based on neural networks and tracking signals

Paper aims This paper presents a nonlinear time series prediction methodology using Neural Networks and Tracking Signals method to detect bias their responsiveness non-random changes in the series. Originality study contributes with an innovative approach of methodology. Furthermore, Design Experiments was applied simulate datasets analyze results Average Run Length, identifying which conditions is efficient. Research Datasets were generated different by changing error The implemented evaluate results. Lastly, case based on total oil grease performed. Main findings showed that proposed effective way process when introduced because mean standard deviation have significant impact Length. Implications for theory practice discussion about since this new technique could be widely used several areas improve forecast accuracy.