Journal of Vocational, Informatics and Computer Education
Vol 4, No 3 (2026): September 2026

Transaction-level Ethereum scam classification using supervised machine learning with leakage-aware preprocessing and class imbalance handling

Lely Priska D. Tampubolon (Perbanas Institute, Indonesia)
Budi Indiarto (Perbanas Institute, Indonesia)
Dwi Atmodjo WP (Perbanas Institute, Indonesia)
Nani Krisnawaty Tachjar (Perbanas Institute, Indonesia)
Winny Purbaratri (Perbanas Institute, Indonesia)
Kevin Arthur Justin (Universitas Pelita Harapan, Indonesia)



Article Info

Publish Date
16 Sep 2026

Abstract

Purpose: This study examines whether native transaction-level attributes can classify scam-labeled and non-scam-labeled Ethereum transactions using supervised machine learning under a controlled benchmarking framework, before graph-derived or address-history representations are introduced. Methods: A public dataset of 71,239 Ethereum transactions was analyzed using eleven numerical and temporal predictors covering value, gas-related attributes, transaction ordering, block metadata, and timestamp-derived characteristics. Logistic Regression, Random Forest, and LightGBM were evaluated under consistent partitioning and leakage-aware preprocessing, with SMOTE applied within training pipelines. Performance was assessed using accuracy, precision, recall, F1-score, and ROC-AUC. Findings: Ensemble models outperformed the linear baseline, indicating that nonlinear relationships among transaction attributes carry useful classification signals. LightGBM achieved the highest accuracy (0.9799), recall (0.9381), F1-score (0.9383), and ROC-AUC (0.9944), while Random Forest performed comparably with higher precision (0.9475). Block-related and gas-related attributes were prominent predictors, although these associations are not causal. Research Implication: The benchmark provides a transparent baseline for assessing whether graph-based, address-history, and temporal representations add predictive value beyond native transaction information, and supports future chronological and address-disjoint validation. Originality: Unlike prior studies relying on account aggregation, graph learning, or learned representations, this study isolates the predictive information contained in compact transaction-native attributes through a controlled, leakage-aware transaction-level benchmark, providing a reference point for quantifying the incremental value of richer representations in Ethereum scam classification.

Copyrights © 2026






Journal Info

Abbrev

VOICE

Publisher

Subject

Computer Science & IT Education

Description

1. Informatics and Computing Research addressing the design, development, implementation, and evaluation of computing technologies relevant to educational, professional, and digital learning environments, including but not limited to: Artificial Intelligence and Machine Learning Deep Learning and ...