Predicting Caffeine-Related Sleep Disruption Using Supervised Machine Learning
Knowledge and Decision Systems with Applications · 07.07.2026 · 2 · 632-641
DOI: 10.59543/wkcd4119 ↗Kurz gefasst
Fachartikel in der Zeitschrift Knowledge and Decision Systems with Applications, online erschienen am 07.07.2026. Verfasst von Zahra Zare und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Caffeine is one of the most widely consumed psychoactive substances, yet itseffects on sleep remain complex and not fully understood. In this study, weinvestigate the relationship between caffeine consumption habits and their im-pact on sleep quality using machine learning models. For this purpose, we use adataset that includes self-reported survey responses from 500 participants, fea-turing variables such as caffeine intake, beverage type, time of day, gender, andage. We frame the problem as a binary classification task to determine whetheran individual’s sleep was negatively affected by caffeine. After data preprocess-ing and feature engineering, we applied and evaluated the performance of threeclassification models: logistic regression, decision tree, and random forest. Weassessed model performances using standard metrics such as accuracy, preci-sion, recall, F1-score, and ROC-AUC. Our results revealed that the random forestclassifier outperformed the other two approaches.
Zitieren
APA
Zare, Z., & Karatas, M. (2026). Predicting Caffeine-Related Sleep Disruption Using Supervised Machine Learning. Knowledge and Decision Systems with Applications, 2, 632-641. https://doi.org/10.59543/wkcd4119
Vancouver
Zare Z, Karatas M. Predicting Caffeine-Related Sleep Disruption Using Supervised Machine Learning. Knowledge and Decision Systems with Applications. 2026;2:632-641. doi:10.59543/wkcd4119
BibTeX
@article{Zare2026,
author = {Zare, Zahra and Karatas, Mumtaz},
title = {Predicting Caffeine-Related Sleep Disruption Using Supervised Machine Learning},
journal = {Knowledge and Decision Systems with Applications},
year = {2026},
volume = {2},
pages = {632--641},
doi = {10.59543/wkcd4119}
}
EUVIMED