Browse Teach Curate

Stacking-Ensemble Multi-Classifier Fusion for ATM Network Quality Assessment

A data-fusion classification pipeline that combines Random Forest, LightGBM, and CatBoost base learners through a stacking meta-classifier, with SMOTE oversampling to handle class imbalance, to detect ATM-network service-quality status from reliability KPIs and sharply reduce false alarms relative to any single model.

KITT Text

Enhancing Precision of Automated Teller Machines Network Quality Assessment: Machine Learning and

An applied machine-learning study that classifies the operational status/quality of Automated Teller Machine (ATM) networks from key performance indicators (availability, reliability, MTTF, MTTR) to …