Recursive Analytics for User Behaviour to Dynamic Stimuli Using a Rolling Window Based Precision
International Journal of Artificial Intelligence and Cognitive Psychology · 14.04.2026 · 2 (1) · 13
DOI: 10.66419/ijaicp.7647 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Artificial Intelligence and Cognitive Psychology, online erschienen am 14.04.2026. Verfasst von Yunus Fatima Abdulsalam und 2 weiteren Autor:innen.
Abstract (Originalsprache)
When recursive loop is coupled with a rolling window approach, where the most recent segment of behavioural data (for example, every 40seconds) is repeatedly re-examined while older observations gradually fall out of scope, the resulting pipeline achieves a level of temporal precision that is both fine-grained and adaptable to rapid shifts in context. The prediction accuracy (AUC ROC) here in this paper shows that the Baseline (static model) lies between 0.71μs and 0.03μs, a recursive model only between 0.78μs and 0.02μs, and a recursive/rolling window at 0.86s-0.01s performance. The mean accumulative error (MAE) in predicting how long a user would linger on a stimulus element dropped by 50% compared with the baseline, indicating a markedly finer grasp of temporal engagement patterns. This shows a user interface (UI) change only when predictive precision exceeds a predefined threshold.
Zitieren
APA
Abdulsalam, Y. F., Isiaka, F., & Makela, L. M. (2026). Recursive Analytics for User Behaviour to Dynamic Stimuli Using a Rolling Window Based Precision. International Journal of Artificial Intelligence and Cognitive Psychology, 2(1), 13. https://doi.org/10.66419/ijaicp.7647
Vancouver
Abdulsalam YF, Isiaka F, Makela LM. Recursive Analytics for User Behaviour to Dynamic Stimuli Using a Rolling Window Based Precision. International Journal of Artificial Intelligence and Cognitive Psychology. 2026;2(1):13. doi:10.66419/ijaicp.7647
BibTeX
@article{Abdulsalam2026,
author = {Abdulsalam, Yunus Fatima and Isiaka, Fatima and Makela, Lauri Matias},
title = {Recursive Analytics for User Behaviour to Dynamic Stimuli Using a Rolling Window Based Precision},
journal = {International Journal of Artificial Intelligence and Cognitive Psychology},
year = {2026},
volume = {2},
number = {1},
pages = {13},
doi = {10.66419/ijaicp.7647}
}
EUVIMED