Enhancing Precision of Automated Teller Machines Network Quality Assessment: Machine Learning and Multi Classifier Fusion Approaches

2025-01-02

AI Summary

To address high state misclassification rates, severe underdetection of rare faults, and an elevated false positive rate (3.56%) in ATM network quality assessment, this paper proposes a SMOTE-enhanced Stacking ensemble framework for multiclass classification. The framework innovatively integrates Random Forest, LightGBM, and CatBoost as base learners and applies SMOTE-based oversampling to minority-class fault instances to jointly enhance model sensitivity to rare events. Experimental results demonstrate that the method reduces the false positive rate to 0.71% and achieves an overall accuracy of 99.29%, significantly mitigating false alarms and improving fault prediction reliability. This work delivers an interpretable, robust, and lightweight solution for intelligent ATM operations, effectively lowering operational costs and strengthening data-driven decision support in banking systems.

Technology Category

• Machine Learning: Ensemble Methods
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Ensuring reliable ATM services is essential for modern banking, directly impacting customer satisfaction and the operational efficiency of financial institutions. This study introduces a data fusion approach that utilizes multi-classifier fusion techniques, with a special focus on the Stacking Classifier, to enhance the reliability of ATM networks. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied, enabling balanced learning for both frequent and rare events. The proposed framework integrates diverse classification models - Random Forest, LightGBM, and CatBoost - within a Stacking Classifier, achieving a dramatic reduction in false alarms from 3.56 percent to just 0.71 percent, along with an outstanding overall accuracy of 99.29 percent. This multi-classifier fusion method synthesizes the strengths of individual models, leading to significant cost savings and improved operational decision-making. By demonstrating the power of machine learning and data fusion in optimizing ATM status detection, this research provides practical and scalable solutions for financial institutions aiming to enhance their ATM network performance and customer satisfaction.

Problem

• ATM Network Quality Assessment
• Accuracy Improvement
• Fault Prediction

Innovation

• Data Fusion
• Stacking Classifier
• SMOTE Technique