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=10 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=

Given the numerous factors that can influence stock prices such as a company's financial health, economic conditions, and the political climate, predicting stock prices can be quite difficult. However, the advent of the newer learning algorithm such as extreme learning machine (ELM) offers the potential to integrate ARIMA and ANN methods within a hybrid framework. This study aims to examine how hybrid time series models and an artificial neural network (ANN)-based ELM performed when analyzing daily Johannesburg Stock Exchange/Financial Times Stock Exchange (JSE/FTSE) closing stock prices over 5 years, from 15 June 2018 to 15 June 2023, encompassing 1,251 data points. The methods used in the study are autoregressive integrated moving average (ARIMA), ANN-based ELM, and a hybrid of ARIMA-ANN-based ELM. The ARIMA method was used to model linearity, while nonlinearity was modeled using an ANN-based ELM. The study further modeled both linearity and non-linearity using the hybrid ARIMA-ANN-based ELM model. The model was then compared to identify the best model for closing stock prices using error matrices. The error metrics revealed that the hybrid ARIMA-ANN-based ELM model performed better than the ARIMA [1, 6, 6] and ANN-based ELM models. It is evident from the literature that better forecasting leads to better policies in the future. Therefore, this study recommends policymakers and practitioners to use the hybrid model, as it yields better results. Furthermore, researchers may also delve into assessing the effectiveness of models by utilizing additional conventional linear models and hybrid variants such as ARIMA-generalized autoregressive conditional heteroskedasticity (GARCH) and ARIMA-EGARCH. Future studies could also integrate these with non-linear models to better capture both linear and non-linear patterns in the data.