Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 12, 2025International Journal of Management and Organizational Research

Forecasting Feeder-Level Outages with Hybrid Time-Series/ML Models: Accuracy, Explainability, and Maintenance Prioritization

View Full Paper
Ask AI
Bookmark
Share

Authors

LGLeeman Takunda GunzoMMMunashe Naphtali MupaTNTendai Nemure

Discussion

Loading...

Member takes

Overview

This analysis finds hybrid models outperform traditional time-series methods for predicting outages, suggesting better maintenance prioritization strategies.

Key Points

  • Hybrid models demonstrated greater accuracy in predicting feeder-level outages compared to classical time-series models.
  • The study showed that the performance and reliability of hybrid models improved significantly when considering nonlinear interactions.
  • Utilizing SHAP for interpretability provided clear insights into risk factors like vegetation density and adverse weather conditions.
  • A robust maintenance prioritization system can be developed based on hybrid model outputs to enhance regulatory compliance.

Cite This Study

Gunzo et al. (2025) studied this question.

synapsesocial.com/papers/68ebabe3155248a327effb03https://doi.org/10.54660/ijmor.2025.4.5.71-78
View Full Paper
Ask AI
Bookmark
Share