Forecasting stock index returns using ARIMA-SVM, ARIMA-ANN, and ARIMA-random forest hybrid models
Samuel Tabot Enow
International Journal of Research in Business and Social Science · 2026 · Vol. 15 / Issue 3 · 226-232
Publication metrics
External links open provider records or DOI searches. Provider counts are not combined. Mendeley readership measures saves, not citations.
Dimensions
Live provider badge. If unavailable, use the Dimensions link above.
Observed 21 Oct 2026, 07:22 UTC
Observed 21 Oct 2026 07:23 UTC
OpenAlex and Mendeley observations refresh on article visits, at most once per 24 hours. Unavailable data is not zero. Google Scholar opens a DOI search.
Citations received by this article, grouped by the year of the citing work. Crossref and OpenAlex lifetime totals remain separate in Publication metrics.
2017–2026 Annual history last updated:
Citations received
OpenAlex · year of the citing work
Hover over a year or focus the chart and use arrow keys to inspect values.
2017–2026 annual-history window. 2026 is year to date. Unknown years have gaps.
View data & coverage
2026 is incomplete. Within a successfully fetched ten-year window, omitted years mean zero. Years beyond a saved observation’s window remain unknown (—). Older citations are excluded, so this chart’s sum may differ from the OpenAlex lifetime total. The date above belongs to this annual history; an unsuccessful refresh keeps the previous observation.
Abstract
The purpose of this study was to investigate the efficacy of hybrid forecasting models that integrate the classical Autoregressive integrated moving average framework, the support vector machines, the artificial neural networks, and random forest for predicting S&P 500 index returns. Utilizing daily share price data from 2015 to 2023, the methodology used a two-stage decomposition process where ARIMA captured linear dependencies, while the ML models projected nonlinear patterns within the residuals. The Out-of-sample analysis revealed that all the hybrid models significantly outperformed their standalone ARIMA benchmark across key accuracy metrics, such as mean absolute error, root mean squared error, and directional accuracy. The ARIMA-RF hybrid achieved the highest predictive accuracy and statistical significance, though it entailed a greater computational cost. The findings confirmed that the hybrid forecasting capabilities to mitigate linear autocorrelation and ARCH effects, offering a robust approach for financial time series forecasting.
Keywords: {'name': 'ARIMA-SVM, ARIMA-ANN, ARIMA-Random, Financial Markets'}
Authors & affiliations
Samuel Tabot Enow
Research Associate, The IIE VEGA School
Deposited references
Supplied references, not a list of publications citing this article.
DOI: 10.1109/TAC.1974.1100705
Box, G. E. P., & Jenkins, G. M. (1976). Time series analysis: Forecasting and control. Holden-Day.
DOI: 10.1023/A:1010933404324
DOI: 10.51594/farj.v6i8.1434
DOI: 10.1080/713665670
DOI: 10.1080/01621459.1979.10482531
DOI: 10.1080/07350015.1995.10524599
DOI: 10.2307/1912773
DOI: 10.32614/CRAN.package.fpp2
DOI: 10.3390/a18080470
DOI: 10.1016/j.eswa.2009.05.044
DOI: 10.1016/S0169-2070(99)00048-5
DOI: 10.1093/biomet/65.2.297
Muhammad, A., Shahab, A., Usama, U., & Omar, K. B. (2021). Role of game theory in stock’s investment: Having loss-aversion bias during the stressed condition. International Journal of Management, 12(3), 872–893.
DOI: 10.1214/aos/1176344136
DOI: 10.1016/S0305-0483(01)00026-3
DOI: 10.1002/0471746193
DOI: 10.1007/978-1-4757-2440-0
DOI: 10.1016/S0925-2312(01)00702-0