eng Science and Education Publishing American Journal of Applied Mathematics and Statistics 2328-7292 2023-08-22 11 2 63 69 10.12691/ajams-11-2-4 AJAMS20231124 article Navoda Hettige dininavo@gmail.com 1 WMND Basnayake 1 Department of Statistics, University of Colombo, Colombo, Sri Lanka Time series forecasting holds a vital significance across diverse domains; however, accurately predicting the future is challenging due to the inherent complexity and non-linear nature of the data. One promising strategy for tackling non-linear time series data is the utilization of hybrid models, which have the potential to enhance forecasting accuracy. In this research paper, a comparative study is conducted, focusing on different approaches to horizontally partition data and fit Long short-term memory artificial neural network models (LSTM ANN). By using simulated data, this study effectively evaluates the efficacy of these approaches. The results demonstrate that DWT-LSTM, EEMD-LSTM, and CEEMDAN-LSTM techniques outperformed the EMD-LSTM and Threshold-LSTM models. http://pubs.sciepub.com/ajams/11/2/4/ajams-11-2-4.pdf complex nonlinear hybrid LSTM