intelligent counterfeit detection through hybrid pattern mining and blockchain traceability: a drug distribution case study

The growing number of exchange points in distribution systems has increased the risk of counterfeit product infiltration, posing serious threats to public health and economic stability. existing anti-counterfeiting strategies, such as blockchain-based traceability and machine learning–driven anomaly detection, remain constrained by vulnerabilities to data manipulation and limited automation. to address these challenges, this study proposes a hybrid approach that integrates sequential pattern mining with blockchain infrastructure for trajectory-based counterfeit detection. the system applies the prefixspan algorithm in combination with the longest common subsequence method to detect anomalous trajectories in product distribution networks. blockchain technology ensures immutability, transparency, and decentralized validation of distribution records, while smart contracts enable automated anomaly detection. experimental evaluation on a real-world dataset, supplemented with simulated counterfeit trajectories, achieves an overall accuracy of 87.4% and an f1-score of 0.843, outperforming existing models. moreover, complexity analysis demonstrates the scalability of the proposed framework by offloading computationally intensive tasks to off-chain processes.