Application of generalised regression neural network for financial time series forecasting: a comprehensive comparison with autoregressive integrated moving average

Hoang D. Le & Ke Nghia Nguyen

International Journal of Data Analysis Techniques and Strategies2026https://doi.org/10.1504/ijdats.2026.151640article
AJG 1
Weight
0.50

What the paper says

Time series forecasting plays a crucial role in fields such as economics, business, and finance. Traditional models like the autoregressive integrated moving average (ARIMA) have been widely used for their accuracy. However, advances in computing and the rise of machine learning (ML) and deep learning (DL) have introduced powerful alternatives. This study examines the performance of a DL-based method - the generalised regression neural network (GRNN) - compared to ARIMA. Results show that GRNN significantly outperforms ARIMA in forecasting accuracy, with an error margin of less than 5%. GRNN also achieves better results across statistical metrics, including mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Additionally, GRNN offers faster training times, making it especially advantageous in scenarios requiring rapid and frequent forecasts. These findings highlight GRNN's potential as a superior tool for time series prediction in dynamic, data-driven environments.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1504/ijdats.2026.151640

Or copy a formatted citation

@article{hoang2026,
  title        = {{Application of generalised regression neural network for financial time series forecasting: a comprehensive comparison with autoregressive integrated moving average}},
  author       = {Hoang D. Le & Ke Nghia Nguyen},
  journal      = {International Journal of Data Analysis Techniques and Strategies},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1504/ijdats.2026.151640},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Application of generalised regression neural network for financial time series forecasting: a comprehensive comparison with autoregressive integrated moving average

Flags are reviewed by the Arbiter methodology team within 5 business days.


Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.