DX Innovation

AI Trade Commodity Classification Methodology: Automated Trade Data Classification Models

AI Commodity Classification: The Core of Trade Data Automation

In trade, HS code (Harmonized System Code) classification is the foundation for determining tariff rates, producing trade statistics, and determining FTA rules of origin. Accurately mapping the world's 5,000+ six-digit HS codes and each country's ten-digit sub-classifications is among the most specialized areas of trade practice, and AI-powered automatic classification has emerged as a flagship challenge in DX innovation.

KOTRA's DX Innovation Lab has developed an NLP (Natural Language Processing)-based automatic commodity classification model that estimates HS codes from product description text alone, and has built a system that also supports cross-conversion with MTI (Korea Trade Statistics Classification) and SITC (Standard International Trade Classification).

5,300+
HS Codes
At the 6-digit level
91%
Classification Accuracy
Top-3 basis
< 1 sec
Processing Speed
Per commodity classification
5M+ records
Training Data
Customs clearance history
4
Supported Systems
HS, MTI, SITC, BEC
KO / EN / ZH
Multilingual Support
Product name recognition

Understanding Trade Commodity Classification Systems

Several commodity classification systems are used in global trade, each serving different purposes. AI automatic classification models learn the mapping relationships between these systems, enabling simultaneous estimation of multiple codes from a single input.

Major Trade Commodity Classification Systems
SystemGoverning BodyCode StructurePrimary Use
HS (Harmonized System)WCO (World Customs Organization)6-digit (10-digit nationally)Tariff imposition, customs clearance, rules of origin
MTI (Korea Trade Statistics Classification)KITA (Korea International Trade Association)6-digitKorean trade statistics and analysis
SITC (Standard International Trade Classification)UN (United Nations)5-digitInternational comparative statistics
BEC (Broad Economic Categories)UN (United Nations)3-digitEconomic analysis, input-output relationships
CPC (Central Product Classification)UN (United Nations)5-digitIntegrated services and goods classification

AI Classification Model Architecture

The AI commodity classification model adopts a three-stage hierarchical classification approach. By reflecting the hierarchical structure of HS codes (chapter → heading → subheading), the model progressively narrows classification from broad to specific, improving overall accuracy.

Text Preprocessing
Product name and description normalization; stopword removal; trade-specialized tokenizer; multilingual unified processing
Embedding Generation
BERT-based trade-specialized embeddings (Trade-BERT); vector generation for product attributes, materials, and uses
Stage 1: Chapter Classification
Select Top-5 candidates from 97 chapters (2-digit); accuracy 98%
Stage 2: Heading Classification
Classify heading (4-digit) within the selected chapter; accuracy 95%
Stage 3: Subheading Classification
Confirm final 6-digit HS code; provide Top-3 candidates with confidence scores
Expert Manual Classification
Time Required5–30 minutes per item
ConsistencyVariation by expert
Bulk ProcessingMax ~50 per day
CostKRW 5,000+ per item
AI Automatic Classification
Time Required< 1 second per item
ConsistencyUniform standard applied
Bulk Processing100,000+ per day
CostUnder KRW 50 per item

Training Data and Model Performance

The accuracy of an AI commodity classification model depends heavily on the quality and volume of training data. KOTRA's DX Innovation Lab secured 5 million+ actual customs clearance records from the Korea Customs Service to train the model, and built industry-specialized glossaries and synonym databases to improve domain-specific accuracy.

AI Classification Model Performance (as of 2025)
Classification StageCode CountTop-1 AccuracyTop-3 AccuracyMain Error Sources
Chapter (2-digit)9796%99%Boundary between similar chapters (e.g., Ch.84 vs Ch.85)
Heading (4-digit)1,200+89%95%Ambiguous product descriptions
Subheading (6-digit)5,300+82%91%Insufficient specification detail
10-digit (Korea)12,000+75%88%Differences in national sub-classifications

Practical Application: Bangladesh Trade Commodity Classification

AI commodity classification is especially valuable in Korea-Bangladesh trade. Bangladesh's tariff system uses HS code sub-classifications that differ from Korea's, and the multi-tier additional duty structure (CD, SD, VAT, AIT, AT) is complex — meaning accurate HS code identification has a direct impact on total landed costs.

01
Automatic HS Code to Tariff Rate Linkage
The AI-classified HS code is automatically linked to the Bangladesh Customs Tariff, instantly calculating the total duty burden: CD (Customs Duty) + SD (Supplementary Duty) + VAT (Value Added Tax) + AIT (Advance Income Tax) + AT (Advance Tax).
02
FTA Rules of Origin Support
While there is no Korea-Bangladesh FTA, certain products are eligible for tariff preferences through APTA (Asia-Pacific Trade Agreement). The AI automatically identifies qualifying products and provides guidance on the applicable rules of origin criteria.
03
MTI-to-HS Code Conversion
KOTRA trade statistics use MTI classification while customs clearance uses HS codes. The AI automatically converts between the two classification systems, resolving code mismatches between market analysis data and operational trade documents.
04
Automatic Detection of Restricted and Prohibited Goods
The AI automatically identifies whether a product falls under Bangladesh's import restriction or prohibition list (Negative List). Pre-shipment verification prevents customs clearance rejection and cargo detention.
Tredocs: AI Trade Document AutomationA trade document automation solution that integrates with HS code classification.
TriBIG Cosine Similarity Market Recommendation AlgorithmHS code-based market analysis and customized export market recommendation technology.
commodity classificationHS codeNLPAI classification modelMTIcustoms
AI Trade Commodity Classification Methodology: Automated Trade Data Classification Models | Dhaka Trade Portal