EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multitask Learning framework for E‐commerce time series analytics: Operational risk, demand forecasting, and anomaly detection

Junzhong He iD, Xiaorui An

PLOS One · 2026

DOI: 10.1371/journal.pone.0352809 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Junzhong He und 1 weiteren Autor:innen. Beteiligte Einrichtung: E-commerce College, Longnan Normal University, Longnan, China. Hauptthemen laut MEDLINE: Commerce, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The study presents MT-PyraRisk, a multi-task learning framework that integrates pyramidal attention mechanisms for cross-border e-commerce risk prediction. The model processes multimodal time-series data through a shared feature extraction layer and task-specific prediction modules, supporting both regression tasks, such as operational risk and demand forecasting, and classification tasks, such as anomaly detection. Experiments were conducted on the Global E-commerce Dataset and the Kaggle Network Traffic Dataset using a sliding-window time-series setting, with the data divided into training, validation, and testing sets at a ratio of 70%, 15%, and 15%, respectively. The model was evaluated using MSE and MAE for regression tasks and Precision, Recall, and F1-score for classification and anomaly detection tasks. Compared with the strong baseline Timesformer, MT-PyraRisk reduced MSE by approximately 4.3% and improved F1-score and Recall by approximately 1.1% and 2.3%, respectively, on the Global E-commerce Dataset. On the Kaggle Network Traffic Dataset, MT-PyraRisk reduced MSE by approximately 5.1% and improved F1-score, Precision, and Recall by approximately 3.3%, 2.2%, and 4.5%, respectively. Ablation results further demonstrate the contribution of the pyramidal attention mechanism, task-specific prediction layers, and joint optimization module, as removing these components led to clear performance degradation. These results indicate that MT-PyraRisk can provide an effective multi-task modeling solution for operational risk forecasting, demand prediction, and anomaly detection in cross-border e-commerce risk management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CommerceMachine LearningData AnalyticsPrediction AlgorithmsForecastingPredictive Learning ModelsHumansAlgorithms

Autor:innen und Institutionen

  • E-commerce College, Longnan Normal University, Longnan, China.
  • Information Center, Longnan Normal University, Longnan, China.

ORCID-Profile: Junzhong He

Zitieren

APA

He, J., & An, X. (2026). A Multitask Learning framework for E‐commerce time series analytics: Operational risk, demand forecasting, and anomaly detection. PLOS One. https://doi.org/10.1371/journal.pone.0352809

Vancouver

He J, An X. A Multitask Learning framework for E‐commerce time series analytics: Operational risk, demand forecasting, and anomaly detection. PLOS One. 2026. doi:10.1371/journal.pone.0352809

BibTeX
@article{He2026,
  author = {He, Junzhong and An, Xiaorui},
  title = {A Multitask Learning framework for E‐commerce time series analytics: Operational risk, demand forecasting, and anomaly detection},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0352809}
}
Kostenlos starten →