AUTHOR=Moseane Onalenna , Tsoku Johannes Tshepiso , Metsileng Daniel 

TITLE=Hybrid time series and ANN-based ELM model on JSE/FTSE closing stock prices

JOURNAL=Frontiers in Applied Mathematics and Statistics

VOLUME=Volume 10 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/applied-mathematics-and-statistics/articles/10.3389/fams.2024.1454595

DOI=10.3389/fams.2024.1454595

ISSN=2297-4687

ABSTRACT=The paper examined how hybrid time series models and ANN-based ELM performed when analysing daily JSE/FTSE closing stock prices over a five-year span, from 15 th June 2018 to 15 th of June 2023, encompassing 1251 data points. The methods used in the paper are ARIMA, ANN based ELM and a hybrid of ARIMA-ANN based ELM. The ARIMA model was used to model the linearity while nonlinearity was modelled using ANN-based ELM. The paper further modelled both the linearity and nonlinearity using the hybrid ARIMA-ANN based ELM model.The model was then compared to identify the best model to be used to modelon the JSE/FTSE closing stock prices using error matrices. The error metrics revealed that the hybrid ARIMA-ANN based ELM model performed better than the ARIMA (6,1,6) and ANN based ELM models. It is evident from literature that better forecasting leads to better policies in the future.Therefore, this paper recommends to the policymakers and practitioners to use the hybrid model as they yield better results. Furthermore, researchers may also delve into assessing the effectiveness of models by utilising additional conventional linear models and hybrid variants like ARIMA-GARCH and ARIMA-EGARCH. Future studies could also integrate these with nonlinear models to better capture both linear and nonlinear patterns in data.