Pattern Recognition of Illicit E-Waste Misclassification in Global Trade Data
By: Muhammad Sukri Bin Ramli
Potential Business Impact:
Finds hidden electronic trash in shipping.
The global trade in electronic and electrical goods is complicated by the challenge of identifying e-waste, which is often misclassified to evade regulations. Traditional analysis methods struggle to discern the underlying patterns of this illicit trade within vast datasets. This research proposes and validates a robust, data-driven framework to segment products and identify goods exhibiting an anomalous "waste signature" a trade pattern defined by a clear 'inverse price-volume'. The core of the framework is an Outlier-Aware Segmentation method, an iterative K-Means approach that first isolates extreme outliers to prevent data skewing and then re-clusters the remaining products to reveal subtle market segments. To quantify risk, a "Waste Score" is developed using a Logistic Regression model that identifies products whose trade signatures are statistically similar to scrap. The findings reveal a consistent four-tier market hierarchy in both Malaysian and global datasets. A key pattern emerged from a comparative analysis: Malaysia's market structure is defined by high-volume bulk commodities, whereas the global market is shaped by high-value capital goods, indicating a unique national specialization. The framework successfully flags finished goods, such as electric generators (HS 8502), that are traded like scrap, providing a targeted list for regulatory scrutiny.
Similar Papers
Green Grid: Smart Tech Meets E-Waste
Human-Computer Interaction
Cleans up old electronics with smart bins and rewards.
Image Segmentation and Classification of E-waste for Training Robots for Waste Segregation
CV and Pattern Recognition
Helps robots sort trash by recognizing e-waste.
Mapping Regional Disparities in Discounted Grocery Products
Physics and Society
Stores sell more meat/dairy in the country.